© 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. 118
    Prev
    Next
    INDEX
    Explanations

    references to audience reactions and demographics

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

    audience response and engagement

    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
    stateProvider
    -0.44
     MonoBehaviour
    -0.43
    AutoresizingMask
    -0.42
    Aiheesta
    -0.39
    delwed
    -0.39
    biť
    -0.38
    SPATH
    -0.38
    SBATCH
    -0.38
     opération
    -0.37
    Preserve
    -0.37
    POSITIVE LOGITS
     audience
    1.52
     audiences
    1.42
     Audience
    1.35
    Audience
    1.34
    audience
    1.28
     Publikum
    1.26
    Audiences
    1.20
     audiencia
    0.97
     penonton
    0.93
     spectators
    0.90
    Activations Density 0.019%

    No Known Activations