Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14151
    Prev
    Next
    INDEX
    Explanations

    symbols and syntactic elements typically used in programming or markup languages

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

    Code with symbols like brackets, colons, and parentheses

    np_acts-logits-general · gemini-2.0-flash

    list items, code structure

    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
    /
    -0.51
    ,...
    -0.46
    ="
    -0.44
    ,…
    -0.44
    -
    -0.44
    ↵↵
    -0.44
    .
    -0.43
    </h3>
    -0.43
    ...
    -0.43
    =”
    -0.42
    POSITIVE LOGITS
    principalColumn
    1.00
    GOTREF
    0.93
     DBNull
    0.92
    ConstraintMaker
    0.91
     Mathf
    0.82
    interopRequire
    0.82
    ReferenceEquals
    0.79
     autorytatywna
    0.78
    GraphicsUnit
    0.78
     Efq
    0.78
    Activations Density 0.198%

    No Known Activations