© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12557
    Prev
    Next
    INDEX
    Explanations

    actions related to proposals, plans, and various evaluations in contexts requiring decision-making or analysis

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

    past participles often followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.65
    itself
    -0.57
     яке
    -0.51
     οποίο
    -0.50
    টি
    -0.50
     something
    -0.48
     Itself
    -0.48
     незавершена
    -0.46
     dieselbe
    -0.46
    有个
    -0.46
    POSITIVE LOGITS
     которые
    1.09
     których
    0.99
     amelyek
    0.94
     които
    0.93
     ones
    0.90
     jotka
    0.89
     denen
    0.87
     которыми
    0.87
     those
    0.86
    those
    0.79
    Activations Density 0.244%

    No Known Activations