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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9555
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory actions.

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

    technical and detailed information related to legal documents and historical circumstances.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases containing "in and" or "and around", typically used to describe locations or areas.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    waitKey
    -0.55
    inaldi
    -0.51
    AppMethodBeat
    -0.51
     HasFactory
    -0.49
    mor
    -0.47
     Pal
    -0.46
    BagConstraints
    -0.46
    pal
    -0.46
    Šaltiniai
    -0.45
    Бахар
    -0.45
    POSITIVE LOGITS
     around
    0.96
     intorno
    0.86
     alrededor
    0.85
     AROUND
    0.83
     autour
    0.81
    around
    0.81
     attorno
    0.81
     Around
    0.80
     вокруг
    0.78
    Around
    0.76
    Activations Density 0.147%

    No Known Activations