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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6286
    Prev
    Next
    INDEX
    Explanations

    assertive statements and punctuation clues that indicate importance or emphasis in the text

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

    emphatic statements ending with a period used to assert something definitively.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ведь
    -0.46
    StreetMap
    -0.46
     disambiguazione
    -0.42
     przecież
    -0.41
    skjaer
    -0.41
     ostavi
    -0.39
     ведь
    -0.39
    ApiModelProperty
    -0.38
     venezolano
    -0.38
    tehende
    -0.38
    POSITIVE LOGITS
     period
    1.69
     Period
    1.68
     PERIOD
    1.56
    period
    1.52
    Period
    1.51
    PERIOD
    1.38
     periods
    1.12
     plain
    1.03
    periods
    0.94
     período
    0.92
    Activations Density 0.254%

    No Known Activations