© 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. 119805
    Prev
    Next
    INDEX
    Explanations

    terms related to fermented foods and their health benefits

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

    fermented products, wine, ale, curd

    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
     motivational
    -0.41
    eventName
    -0.38
    ciens
    -0.36
    épend
    -0.36
    elementAt
    -0.35
     matrícula
    -0.35
     blessure
    -0.34
    incenti
    -0.34
    nosaurus
    -0.34
     tunn
    -0.34
    POSITIVE LOGITS
     defaultstate
    0.57
     createSlice
    0.55
    ScopeManager
    0.52
    msgTypes
    0.49
    bucha
    0.47
    Portale
    0.47
    createServer
    0.46
    IUrlHelper
    0.46
    ServletException
    0.46
    CPtr
    0.45
    Activations Density 0.157%

    No Known Activations