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. 77181
    Prev
    Next
    INDEX
    Explanations

    varied uses of parentheses and dashes in 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
     against
    -0.35
     invitation
    -0.35
     recept
    -0.31
     invoice
    -0.30
    EndContext
    -0.29
     response
    -0.29
     revenu
    -0.28
     situation
    -0.28
     letter
    -0.28
     Invitation
    -0.28
    POSITIVE LOGITS
    ftagPool
    0.79
     pinulongan
    0.79
    fjspx
    0.70
     såsom
    0.69
    RuleContext
    0.68
     nahilalakip
    0.66
     فريبيس
    0.66
    цездатний
    0.65
     including
    0.64
    including
    0.63
    Activations Density 0.079%

    No Known Activations