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. 45432
    Prev
    Next
    INDEX
    Explanations

    references to legacy and its implications in various contexts

    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
     Савезне
    -0.46
    addButton
    -0.46
    ThroughAttribute
    -0.44
    atimes
    -0.43
    phones
    -0.43
     Middlesbrough
    -0.43
     Button
    -0.41
    Button
    -0.40
     Consumer
    -0.40
     Citroen
    -0.39
    POSITIVE LOGITS
     legacy
    1.20
     Legacy
    1.19
    Legacy
    1.09
     legacies
    1.02
    legacy
    1.02
     legado
    0.96
     heritage
    0.88
    ritage
    0.84
    ITAGE
    0.81
     незавершена
    0.76
    Activations Density 0.004%

    No Known Activations