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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1910
    Prev
    Next
    INDEX
    Explanations

    terms and details related to experimental procedures and biological experiments involving laboratory animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toekomst
    -0.54
     zijne
    -0.53
    berdayakan
    -0.52
    altezza
    -0.52
     pinulongan
    -0.50
     hoogte
    -0.49
     rând
    -0.48
     goederen
    -0.46
    addCriterion
    -0.45
     mijne
    -0.45
    POSITIVE LOGITS
     specialized
    0.43
     administ
    0.42
    ępnie
    0.42
     eligible
    0.40
     was
    0.40
    synthesize
    0.40
    IContainer
    0.40
     authorized
    0.40
    postsleuth
    0.39
     manually
    0.39
    Activations Density 3.981%

    No Known Activations