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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 14078
    Prev
    Next
    INDEX
    Explanations

    instances of agreement and consensus among individuals or groups

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

    Preceding tokens of "agree" or agreement

    np_acts-logits-general · gemini-2.0-flash

    expressing agreement or disagreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    älde
    -0.48
    روابط
    -0.46
    jspx
    -0.44
    OrUpdate
    -0.43
     Rücks
    -0.43
    AutoField
    -0.43
    opis
    -0.43
    foy
    -0.43
    //
    -0.42
    下一篇
    -0.42
    POSITIVE LOGITS
     agree
    3.23
     agrees
    2.88
     agreed
    2.74
     agreeing
    2.71
     Agree
    2.70
    agree
    2.61
    Agree
    2.55
     agreement
    2.52
    agreed
    2.47
     Agreed
    2.38
    Activations Density 0.392%

    No Known Activations