© 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. 20-GEMMASCOPE-RES-131K
    11. 75563
    Prev
    Next
    INDEX
    Explanations

    terms related to various technical concepts and their specific attributes or measurements

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

    specifying adjacent, difference, degree, motions, sized, specific, larger, associated, medical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.67
    翻攝
    -0.62
    jfree
    -0.59
     AssemblyTitle
    -0.58
    ########.
    -0.58
    Filmografie
    -0.57
    Rujuakan
    -0.57
    IndentedString
    -0.56
    webElementGuid
    -0.56
     виправивши
    -0.55
    POSITIVE LOGITS
    pfung
    0.40
    NT
    0.33
    DLL
    0.31
    carril
    0.31
     مس
    0.29
    PF
    0.28
    nt
    0.28
     muni
    0.28
    Combo
    0.28
    一生
    0.28
    Activations Density 0.381%

    No Known Activations