© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 38497
    Prev
    Next
    INDEX
    Explanations

    commands or requests related to user actions and site functionality

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

    requests and calls to action

    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
    ngdoc
    -0.40
    dismo
    -0.35
    Scénario
    -0.35
     booze
    -0.33
     DEV
    -0.32
    multirow
    -0.32
    SerializeField
    -0.32
    Kamu
    -0.31
    ObjectContext
    -0.31
    Gonna
    -0.31
    POSITIVE LOGITS
     Infórmanos
    0.91
     please
    0.85
     Please
    0.82
    Please
    0.75
    please
    0.72
     пожалуйста
    0.72
     PLEASE
    0.68
    PLEASE
    0.66
     veuillez
    0.66
     oprot
    0.66
    Activations Density 0.047%

    No Known Activations