© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10732
    Prev
    Next
    INDEX
    Explanations

    questions or statements that start with "what" or "why" and relate to reasoning or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    memoized
    -0.71
    IndentedString
    -0.59
    Clik
    -0.54
     Мексичка
    -0.54
    hilangan
    -0.53
    expandindo
    -0.53
    Portály
    -0.51
     δὲ
    -0.51
    BeginContext
    -0.50
    enterOuterAlt
    -0.49
    POSITIVE LOGITS
     للمعارف
    0.61
    DoubleQuotes
    0.60
    satunya
    0.59
     why
    0.58
     السب
    0.56
     właśnie
    0.54
     reason
    0.51
     فريبيس
    0.51
    ziplin
    0.51
     Einbau
    0.50
    Activations Density 0.318%

    No Known Activations