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. 29896
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and parameters related to molecular biology and nanotechnology

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

    spatial scale calculation

    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
    ientôt
    -0.73
     feroit
    -0.57
    pecabe
    -0.55
     pouvoit
    -0.55
     auroit
    -0.54
    ésult
    -0.52
    alakip
    -0.51
    WriteTagHelper
    -0.50
    Personendaten
    -0.50
     leão
    -0.50
    POSITIVE LOGITS
    참고
    0.55
    enterOuterAlt
    0.54
     SDA
    0.52
    NameInMap
    0.49
     MatDialog
    0.48
     cic
    0.48
     ADC
    0.48
     OSP
    0.48
    立った
    0.48
     ACI
    0.48
    Activations Density 0.483%

    No Known Activations