© 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. 31-GEMMASCOPE-RES-131K
    6. 64398
    Prev
    Next
    INDEX
    Explanations

    references to the evaluation and effectiveness of medical treatments

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

    effectiveness and ineffectiveness

    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
     Chwiliwch
    -0.60
     wireType
    -0.53
     astore
    -0.48
     arşivlendi
    -0.46
    cessite
    -0.44
    ftagPool
    -0.44
    leisure
    -0.44
    ̈́
    -0.43
    richTextPanel
    -0.43
     protoimpl
    -0.42
    POSITIVE LOGITS
     effectiveness
    2.42
    Effectiveness
    2.09
     efficacy
    2.08
     Effectiveness
    2.08
     effective
    2.06
    effectiveness
    1.96
    effective
    1.73
    Effective
    1.72
     Effective
    1.71
     Efficacy
    1.69
    Activations Density 0.443%

    No Known Activations