© 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. 56274
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of expression and co-expression in biochemistry or genetics contexts

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

    co-expression and co-occurrence

    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
     defaultstate
    -0.52
    GenerationType
    -0.51
    PerformLayout
    -0.50
     الرياضيه
    -0.46
    marvin
    -0.46
     uska
    -0.44
     intptr
    -0.44
    djangoproject
    -0.44
     zijne
    -0.43
    BeginInit
    -0.43
    POSITIVE LOGITS
     coexist
    0.76
     coexistence
    0.73
     coc
    0.64
     co
    0.61
    partner
    0.60
     partner
    0.60
     partners
    0.60
     coö
    0.59
    Sharing
    0.59
     copro
    0.58
    Activations Density 0.038%

    No Known Activations