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. 21-GEMMASCOPE-RES-16K
    6. 14970
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and punctuation in code or programming language scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     căr
    -0.61
    ."—
    -0.61
    ⓘ
    -0.60
     hjemme
    -0.59
    findpost
    -0.57
    "—
    -0.57
    évaluateur
    -0.56
    ⓧ
    -0.56
     passés
    -0.55
    ReusableCell
    -0.54
    POSITIVE LOGITS
    console
    1.07
     console
    1.01
    let
    0.79
     let
    0.78
    const
    0.76
     const
    0.72
     !==
    0.68
    (`${
    0.67
    setTimeout
    0.65
     window
    0.64
    Activations Density 0.099%

    No Known Activations