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

    Neuronpedia

    APICircuit 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. 35346
    Prev
    Next
    INDEX
    Explanations

    economic indicators and discussions around fiscal policies and their impact on employment and wealth distribution

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

    economic policy and reform

    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
    argout
    -0.40
     TextEditing
    -0.39
    TextEditing
    -0.35
    %}
    -0.34
    indrome
    -0.33
    …”
    -0.32
     team
    -0.31
     %}
    -0.31
     Au
    -0.31
     Qu
    -0.31
    POSITIVE LOGITS
    exitRule
    0.62
    Hentet
    0.61
     CURIAM
    0.60
    ритори
    0.58
    RegistryLite
    0.58
    
    0.56
     estekak
    0.54
    lanatory
    0.52
    letzt
    0.51
    expandindo
    0.50
    Activations Density 0.252%

    No Known Activations