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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 12666
    Prev
    Next
    INDEX
    Explanations

    phrases related to duration and ongoing recognition

    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
     biologique
    -0.36
     maire
    -0.32
     démoc
    -0.31
    neté
    -0.31
     presupuesto
    -0.30
    érité
    -0.30
     pazar
    -0.30
     licencia
    -0.29
     posibilidades
    -0.29
    fø
    -0.29
    POSITIVE LOGITS
    Already
    0.69
     already
    0.69
     Already
    0.68
     ModelExpression
    0.66
    already
    0.66
     ALREADY
    0.61
    早就
    0.61
    ViewFeatures
    0.59
    早已
    0.58
    ALREADY
    0.58
    Activations Density 0.520%

    No Known Activations