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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6701
    Prev
    Next
    INDEX
    Explanations

    sentences that express thoughts or inquiries about existence and understanding.

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

    programming code snippets and technical explanations.

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

    sentence-ending punctuation, particularly periods, question marks, and exclamation points.

    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
     doInBackground
    -0.59
    ねて
    -0.57
    …
    -0.56
     Einfluß
    -0.56
    stuhl
    -0.55
     LayoutInflater
    -0.54
    RTCF
    -0.54
     ...
    -0.54
    ...
    -0.53
    StateToProps
    -0.53
    POSITIVE LOGITS
     Uh
    0.68
    Uh
    0.65
    Um
    0.64
     Okay
    0.63
     Um
    0.63
     okay
    0.63
    Okay
    0.62
    Personendaten
    0.61
     Oh
    0.59
     resourceCulture
    0.58
    Activations Density 0.046%

    No Known Activations