© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15913
    Prev
    Next
    INDEX
    Explanations

    references to pagination in code or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code that manipulates collections/lists, such as checking their size/length, indexing/accessing elements, iterating/mapping over them, and handling pagination.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    Looking at the activations, this neuron strongly activates on code patterns where data structures are being accessed, assigned, or checked, particularly: - Property access chains (e.g., `data.length`, `state.data`, `result.data.restaurants`) - Assignment operations

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -0.54
     незавершена
    -0.49
    saraba
    -0.48
    /**
    -0.47
     ویکی‌پدی
    -0.47
    SharedDtor
    -0.47
    AxisAlignment
    -0.47
    AnimationsModule
    -0.46
     CONTEM
    -0.45
    PreferredItem
    -0.45
    POSITIVE LOGITS
     jazdy
    0.42
     verzame
    0.41
     inhoud
    0.40
     verhalen
    0.40
     groupings
    0.40
    ientôt
    0.39
     själva
    0.39
     tranches
    0.38
     gegeven
    0.38
     geleverd
    0.37
    Activations Density 0.145%

    No Known Activations