© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10999
    Prev
    Next
    INDEX
    Explanations

    phrases related to representation or action taken on someone's behalf

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

    Pronominal reference

    np_acts-logits-general · gemini-2.0-flash

    acting on behalf of others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BindingResult
    -0.38
    AnimationsModule
    -0.36
    astify
    -0.35
     pan
    -0.33
     useContext
    -0.33
    ParallelGroup
    -0.32
    MLLoader
    -0.31
    */].
    -0.31
     posibil
    -0.31
     isKindOfClass
    -0.30
    POSITIVE LOGITS
     ModelExpression
    0.72
     proxy
    0.68
     behalf
    0.64
     Proxy
    0.60
    proxy
    0.56
     للاسماء
    0.54
     hộ
    0.52
     dAtA
    0.51
    出版年
    0.51
    aarrggbb
    0.51
    Activations Density 0.355%

    No Known Activations