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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35037
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or figures related to sports

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

    team names after scores

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tagHelperRunner
    -0.77
     estekak
    -0.73
    Tikang
    -0.72
    AndEndTag
    -0.71
     nakalista
    -0.65
    fjspx
    -0.64
    읗
    -0.58
    Хьажоргаш
    -0.57
    __':
    
    -0.54
    IVEREF
    -0.54
    POSITIVE LOGITS
    isnull
    0.35
    partements
    0.34
    pres
    0.34
     PRES
    0.33
    eller
    0.32
    ...
    0.32
    adhy
    0.31
     private
    0.31
    oz
    0.31
     vis
    0.31
    Activations Density 0.049%

    No Known Activations