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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 11112
    Prev
    Next
    INDEX
    Explanations

    bullet point formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    â
    -0.85
    —
    -0.81
    ?’
    -0.77
    *****
    -0.73
    ’
    -0.73
    !’
    -0.73
     !
    -0.72
    

    -0.69
    <b>
    -0.69
    AppMethodBeat
    -0.66
    POSITIVE LOGITS
     ·
    2.19
    ··
    1.81
    ·
    1.75
     ··
    1.54
    ····
    1.50
    ···
    1.42
    ······
    1.28
    DockStyle
    1.25
    VIAF
    1.12
    middot
    1.12
    Activations Density 0.089%

    No Known Activations