Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6896
    Prev
    Next
    INDEX
    Explanations

    references to specific pharmaceutical companies and software configuration settings

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

    setAccessibleName, exerts, evoked

    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
    eradish
    -0.60
     viewType
    -0.57
    ffichage
    -0.51
     Infórmanos
    -0.51
     matur
    -0.46
     Murillo
    -0.46
    новништво
    -0.44
     Dubois
    -0.44
     daire
    -0.44
     Honig
    -0.44
    POSITIVE LOGITS
    ResponseWriter
    1.02
    GetKeyDown
    0.85
    createServer
    0.69
    NewReader
    0.61
    ########.
    0.57
    Configurer
    0.57
     strtotime
    0.56
    SequentialGroup
    0.56
    Bayer
    0.56
     FormBuilder
    0.55
    Activations Density 0.000%

    No Known Activations