© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    statements or questions expressing skepticism or concern about trends in consumer technology

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

    end of sentences marked with periods.

    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
    WireFormatLite
    -0.68
    RTGC
    -0.63
     surla
    -0.59
    Bibitem
    -0.59
    +#+
    -0.58
    ApiModelProperty
    -0.58
    yntaxException
    -0.57
    󰀄
    -0.57
    帖最后由
    -0.57
    Cyfarwyddwr
    -0.57
    POSITIVE LOGITS
     Seems
    0.69
    Personally
    0.65
     Personally
    0.64
    Seems
    0.62
     I
    0.62
     seems
    0.60
    それにしても
    0.55
    Maybe
    0.54
     Maybe
    0.54
    seems
    0.53
    Activations Density 0.604%

    No Known Activations