© 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. 7-GEMMASCOPE-RES-16K
    6. 15791
    Prev
    Next
    INDEX
    Explanations

    references to sources of information or authority in reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.62
    WillAppear
    -0.56
    ContentAsync
    -0.56
     تضيفلها
    -0.51
    ecute
    -0.51
     initComponents
    -0.51
    parency
    -0.50
    ftagPool
    -0.50
    IBOutlet
    -0.50
    Ecotoxicity
    -0.49
    POSITIVE LOGITS
     sources
    0.69
     fuentes
    0.57
     insiders
    0.52
    Sources
    0.51
    sources
    0.51
     Sources
    0.48
     sumber
    0.47
     source
    0.45
     fontes
    0.45
     informants
    0.44
    Activations Density 0.203%

    No Known Activations