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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 45535
    Prev
    Next
    INDEX
    Explanations

    function calls in code

    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
    MessageTagHelper
    -0.60
     estekak
    -0.59
    HomeAsUpEnabled
    -0.55
    awtextra
    -0.51
     recoveries
    -0.50
    JsonPropertyName
    -0.50
    })));
    -0.50
    AsUp
    -0.48
     uLocal
    -0.48
    Bakgrunnsstoff
    -0.48
    POSITIVE LOGITS
    BuildContext
    0.43
     AttributeSet
    0.42
    AutoScaleMode
    0.40
    MenuInflater
    0.37
     induk
    0.36
    (
    0.36
     royaltyfri
    0.35
    Biographie
    0.35
     تعدى
    0.34
     Cataloging
    0.34
    Activations Density 0.000%

    No Known Activations