© 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. 64907
    Prev
    Next
    INDEX
    Explanations

    specific biochemical or genetic markers associated with risk factors in cardiovascular health

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

    uppercase acronyms and technical terms

    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
    Enlaces
    -0.62
    httphttps
    -0.60
    ագրություններ
    -0.52
    Lähteet
    -0.52
     nahilalakip
    -0.51
     שוליים
    -0.51
     snippetHide
    -0.46
     ligiloj
    -0.46
     étrangers
    -0.45
    İstinadlar
    -0.44
    POSITIVE LOGITS
    A
    0.39
     A
    0.38
     المعيارى
    0.37
     RC
    0.36
    xAA
    0.36
    XB
    0.36
    AA
    0.35
    RB
    0.35
    RC
    0.35
     XA
    0.34
    Activations Density 0.187%

    No Known Activations