© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1520
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those related to object and method definitions

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

    Code-related terms and identifiers in different programming languages

    np_acts-logits-general · gemini-2.0-flash

    type prefixes like `_`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Far
    -0.43
     far
    -0.42
     rend
    -0.41
    Far
    -0.41
     soud
    -0.38
    軟
    -0.38
    rager
    -0.37
    ã
    -0.37
    aneamente
    -0.36
    甘
    -0.36
    POSITIVE LOGITS
     Theſe
    0.80
     pouvoit
    0.74
     rhestr
    0.73
    OrBuilder
    0.73
     auroit
    0.70
     feroit
    0.70
     Monfieur
    0.69
     BoxDecoration
    0.65
    Filmografie
    0.64
     Majefty
    0.64
    Activations Density 0.352%

    No Known Activations