© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14409
    Prev
    Next
    INDEX
    Explanations

    script-related keywords, particularly those involved in routing configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    awtextra
    -0.81
    TextWatcher
    -0.73
    CodedInputStream
    -0.72
    oneofs
    -0.69
    ########.
    -0.68
    EndGlobalSection
    -0.66
     oprot
    -0.65
     religione
    -0.65
    setVerticalGroup
    -0.64
    __':
    -0.63
    POSITIVE LOGITS
     oignons
    0.50
     dédié
    0.44
     wipes
    0.43
    triangleq
    0.43
    wirtschaft
    0.42
    equila
    0.42
     scenes
    0.42
    WZ
    0.41
     eccell
    0.41
     zubehör
    0.41
    Activations Density 0.072%

    No Known Activations