© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 85076
    Prev
    Next
    INDEX
    Explanations

    references to prominent political figures or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mike Pompeo, Top Chef, Google code, bacteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.98
     AssemblyCulture
    -0.97
    ScopeManager
    -0.94
    Personendaten
    -0.93
     snippetHide
    -0.89
    脚注の使い方
    -0.89
    ロウィン
    -0.88
    ISupport
    -0.87
     defaultstate
    -0.87
    parsedMessage
    -0.81
    POSITIVE LOGITS
     MediatR
    0.51
    ourtney
    0.45
    tearDown
    0.39
    ppins
    0.34
     Pompeo
    0.33
    OrFail
    0.32
     girls
    0.29
     uska
    0.28
    </strong>
    0.27
     couple
    0.26
    Activations Density 0.007%

    No Known Activations