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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45881
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terminology related to various topics, including environmental science, medical research, and platform mechanics

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

    pharmaceuticals and specific 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
    typeDefinition
    -0.31
    Source
    -0.27
     Spez
    -0.26
    enregistrement
    -0.24
     Source
    -0.24
     Economía
    -0.24
    error
    -0.24
    ess
    -0.24
     dépôt
    -0.24
     feil
    -0.23
    POSITIVE LOGITS
     queſta
    0.79
    principalTable
    0.78
    OGND
    0.72
     snippetHide
    0.71
    GEBURTS
    0.71
    ðsíða
    0.70
     لينك
    0.70
     CreateTagHelper
    0.69
    wiliwch
    0.69
    Tembelea
    0.68
    Activations Density 0.044%

    No Known Activations