© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1802
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and database entries

    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
    ViewImports
    -0.70
    ConstraintMaker
    -0.66
     ModelExpression
    -0.65
     estekak
    -0.64
    الحياه
    -0.54
    TagMode
    -0.54
    تقاوى
    -0.54
    :✨
    -0.52
    haikusbot
    -0.51
     Roskov
    -0.50
    POSITIVE LOGITS
     InputDecoration
    0.67
     ſtate
    0.65
    ſelf
    0.57
     iParam
    0.56
     napoli
    0.54
     Picchu
    0.53
     otomatig
    0.52
     houſe
    0.52
     Houſe
    0.51
    quations
    0.51
    Activations Density 1.411%

    No Known Activations