© 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. 38-GEMMASCOPE-RES-16K
    11. 10264
    Prev
    Next
    INDEX
    Explanations

    references to openings and events related to public gatherings and facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.71
    TRAILING
    -0.53
    twimg
    -0.53
     AssemblyCulture
    -0.52
     ModelExpression
    -0.44
     Administrativna
    -0.40
    Derbyniad
    -0.38
    mybatisplus
    -0.37
    outState
    -0.37
    zzleHttp
    -0.37
    POSITIVE LOGITS
     opening
    4.03
     opened
    3.58
     Opening
    3.47
    opening
    3.44
    Opening
    3.44
     opens
    3.23
     OPENING
    3.22
    opened
    2.97
     Opened
    2.95
    OPENING
    2.92
    Activations Density 1.826%

    No Known Activations