Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45766
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and its characteristics

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

    scientific research contexts

    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
     perks
    -0.56
     barge
    -0.54
    combo
    -0.53
    Mez
    -0.52
     RANGE
    -0.52
     olmaz
    -0.52
    ㎏
    -0.52
     Sauce
    -0.52
     clauses
    -0.51
     们
    -0.51
    POSITIVE LOGITS
    scientific
    0.97
    Scientific
    0.94
     scientific
    0.93
     Scientific
    0.93
     SCIENTIFIC
    0.81
    cientific
    0.78
    neurial
    0.65
     científicas
    0.62
    peutic
    0.60
    riotic
    0.59
    Activations Density 0.012%

    No Known Activations