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. 124863
    Prev
    Next
    INDEX
    Explanations

    mentions of the presence of specific entities or factors within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ainfi
    -0.69
     esfuer
    -0.56
    mær
    -0.55
     esprits
    -0.52
    cartão
    -0.52
     zijne
    -0.51
    intera
    -0.50
     vôtre
    -0.50
     nôtre
    -0.50
     Fazit
    -0.50
    POSITIVE LOGITS
     presence
    0.85
     Presence
    0.82
     наличии
    0.74
     наличие
    0.71
     наличи
    0.68
     Existence
    0.68
    presence
    0.68
    Existence
    0.67
    Presence
    0.67
     présence
    0.63
    Activations Density 0.051%

    No Known Activations