© 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. 31-GEMMASCOPE-RES-16K
    11. 14458
    Prev
    Next
    INDEX
    Explanations

    references to data structures and collections

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

    array or collection data structure declarations and assignments in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    variable declarations and initializations in programming code, particularly collections like arrays, maps, and objects.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    plural collection-style identifiers in source code, especially when declaring or accessing maps, lists, arrays, or related structures.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.49
     ſtate
    -0.47
     enfans
    -0.43
     faſt
    -0.42
     pleaſure
    -0.41
     ftate
    -0.41
    лючение
    -0.40
     deſt
    -0.39
    ộm
    -0.39
     ſta
    -0.39
    POSITIVE LOGITS
    capes
    0.66
    cales
    0.65
    ides
    0.60
    iders
    0.57
    hips
    0.57
    ubs
    0.56
    hops
    0.56
    lides
    0.56
    aves
    0.55
    ticks
    0.55
    Activations Density 0.395%

    No Known Activations