© 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. 35-GEMMASCOPE-RES-16K
    11. 7640
    Prev
    Next
    INDEX
    Explanations

    references to clubs and organizations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.33
    격
    -0.30
    MarshalTo
    -0.28
    komna
    -0.27
    particle
    -0.27
    󠁣
    -0.27
    toggler
    -0.27
     Cauchy
    -0.26
    COMPOS
    -0.26
    dataIndex
    -0.26
    POSITIVE LOGITS
     club
    3.53
     Club
    3.09
    club
    3.06
     CLUB
    2.98
     clubs
    2.98
    Club
    2.92
     klub
    2.67
     Clubs
    2.66
    CLUB
    2.59
     clube
    2.55
    Activations Density 0.355%

    No Known Activations