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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4848
    Prev
    Next
    INDEX
    Explanations

    CSS formatting and style properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     OMITBAD
    -0.50
    RegressionTest
    -0.46
    pecabe
    -0.46
    SpringRunner
    -0.46
    Autoritní
    -0.46
     kapture
    -0.46
    attutto
    -0.45
     parachoque
    -0.44
    Specifiche
    -0.44
    mybatisplus
    -0.44
    POSITIVE LOGITS
    __*/
    0.49
    ConstraintMaker
    0.49
    帖最后由
    0.48
    rosin
    0.47
    ularia
    0.47
     sugges
    0.47
     
    0.47
    HtmlAttribute
    0.46
     ideal
    0.46
    하며
    0.46
    Activations Density 0.007%

    No Known Activations