© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 32140
    Prev
    Next
    INDEX
    Explanations

    references to personal childhood experiences and aspirations

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

    describing people's roles or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     كومونز
    -0.71
     BrowserModule
    -0.60
    RenderAtEndOf
    -0.57
     increí
    -0.52
    FTFY
    -0.51
    Bakgrunnsstoff
    -0.51
     للاسماء
    -0.50
    SharedDtor
    -0.50
    ]")]
    -0.49
    әрмәләр
    -0.47
    POSITIVE LOGITS
     me
    0.37
    setBackground
    0.36
    EndContext
    0.35
    complexType
    0.34
    ceğine
    0.33
    رشف
    0.33
     Man
    0.33
    <%@
    0.31
    här
    0.31
    BASEPATH
    0.31
    Activations Density 0.039%

    No Known Activations