© 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. 20-GEMMASCOPE-RES-131K
    6. 53383
    Prev
    Next
    INDEX
    Explanations

    technical code elements, specifically related to connection strings and database configuration

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

    code snippets 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 @ 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
    oa̍t
    -0.50
     resultCode
    -0.46
    TagMode
    -0.44
     ProtoMessage
    -0.43
     endforeach
    -0.42
     Blades
    -0.42
    migrationBuilder
    -0.41
    MLLoader
    -0.41
     AssemblyCulture
    -0.40
     bezeichneter
    -0.40
    POSITIVE LOGITS
     franquicia
    0.55
    makeConstraints
    0.51
    sidemargin
    0.47
    vų
    0.45
    CppMethod
    0.44
     virtuales
    0.43
    的主要
    0.43
     vectorielle
    0.43
     piattaforma
    0.43
     berbahaya
    0.42
    Activations Density 0.013%

    No Known Activations