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. 45496
    Prev
    Next
    INDEX
    Explanations

    instances of family relationships and significant life events

    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
    [%
    -0.32
     själva
    -0.30
    iecie
    -0.29
     Ten
    -0.28
     <<<<<<<<<<<<<<
    -0.28
    Autoritní
    -0.28
    vábbi
    -0.27
     modern
    -0.25
    stalt
    -0.25
    نمای
    -0.24
    POSITIVE LOGITS
    principalColumn
    0.91
     lost
    0.77
    lost
    0.74
    niſſe
    0.73
     deſſen
    0.72
    iſchen
    0.70
    ſicht
    0.70
     loss
    0.70
    iſche
    0.69
    ValueStyle
    0.69
    Activations Density 0.035%

    No Known Activations