© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 3207
    Prev
    Next
    INDEX
    Explanations

    references to financial amounts, particularly in the context of U.S. currency and economic indicators

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

    US and American contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     HasFactory
    -0.76
    yntaxException
    -0.76
     الحره
    -0.74
    (!__
    -0.72
    InitVars
    -0.70
    帖最后由
    -0.69
    MigrationBuilder
    -0.69
    OGND
    -0.68
     tartalomajánló
    -0.67
     BoxFit
    -0.67
    POSITIVE LOGITS
     American
    2.03
     US
    1.92
     Americans
    1.84
     USA
    1.82
     America
    1.82
    American
    1.80
     американ
    1.66
     american
    1.65
    USA
    1.64
     amerikan
    1.63
    Activations Density 1.110%

    No Known Activations