© 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. 11-GEMMASCOPE-RES-16K
    11. 4952
    Prev
    Next
    INDEX
    Explanations

    references to incidents or occurrences, particularly in the context of legal or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ButtonModule
    -0.50
    Cartney
    -0.47
    ButterKnife
    -0.47
    saveButton
    -0.47
    Skocz
    -0.44
     Presbyter
    -0.43
    '%(
    -0.42
     Reno
    -0.42
    Reno
    -0.41
     übere
    -0.41
    POSITIVE LOGITS
     incident
    1.07
     incidents
    0.98
     scandals
    0.94
     controversy
    0.93
     Incident
    0.91
     scandal
    0.85
    incident
    0.85
     controversies
    0.83
     Incidents
    0.83
     conflict
    0.81
    Activations Density 0.250%

    No Known Activations