© 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. 13-GEMMASCOPE-RES-16K
    6. 8605
    Prev
    Next
    INDEX
    Explanations

    mentions of racial disparities in justifiable homicide cases and associated statistical analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.59
    +#+#
    -0.53
     թվական
    -0.52
    RegressionTest
    -0.50
    parsedMessage
    -0.49
    IBOutlet
    -0.48
    uação
    -0.48
    Espèce
    -0.47
    ızlık
    -0.45
    WebElementEntity
    -0.44
    POSITIVE LOGITS
     vs
    0.47
     versus
    0.47
     ostavi
    0.44
    versus
    0.40
    UIControlState
    0.39
     néglig
    0.39
    Interv
    0.38
     avis
    0.38
    vs
    0.37
    𝗫
    0.37
    Activations Density 1.055%

    No Known Activations