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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15430
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures like functions, variables, and classes

    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
    exitRule
    -0.67
     للمعارف
    -0.65
    endpush
    -0.62
     queſta
    -0.54
     estekak
    -0.53
     autorytatywna
    -0.51
    PyExc
    -0.49
     ſind
    -0.49
    ########.
    -0.48
     ſche
    -0.48
    POSITIVE LOGITS
    hyrchwyd
    0.49
     ويكيپيديا
    0.47
    AnchorStyles
    0.46
     Wicidata
    0.42
    abestanden
    0.37
     sogen
    0.36
    曖昧さ回避
    0.36
    渡
    0.35
     FUCKING
    0.35
     poked
    0.35
    Activations Density 0.854%

    No Known Activations