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. 14-GEMMASCOPE-RES-16K
    6. 13019
    Prev
    Next
    INDEX
    Explanations

    references to constancy and repetitive actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muffins
    -0.80
     vnto
    -0.77
    createCanvas
    -0.76
     âgées
    -0.74
     Berthe
    -0.73
     SUT
    -0.72
     Numb
    -0.71
    ävän
    -0.71
    endphp
    -0.71
     onComplete
    -0.69
    POSITIVE LOGITS
     Always
    1.36
     ALWAYS
    1.31
     always
    1.30
    Always
    1.24
    always
    1.23
    ALWAYS
    1.20
     luôn
    1.00
    Siempre
    0.95
    deauna
    0.93
     Siempre
    0.92
    Activations Density 0.058%

    No Known Activations