© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 5119
    Prev
    Next
    INDEX
    Explanations

    numeric values and statistical data related to medical or health-related studies

    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
    SourceChecksum
    -0.68
    ########.
    -0.44
     Teich
    -0.40
    endpush
    -0.38
    viders
    -0.37
    VYMaps
    -0.36
    WithIOException
    -0.36
    AddField
    -0.35
     regulatory
    -0.35
    mtrl
    -0.35
    POSITIVE LOGITS
    aarrggbb
    0.53
    Microkernel
    0.44
    RegressionTest
    0.43
    Autoritní
    0.40
     uska
    0.40
    instancetype
    0.40
    lawesi
    0.39
     Wiktionnaire
    0.39
    Toponymie
    0.39
     informée
    0.38
    Activations Density 2.697%

    No Known Activations