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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 920
    Prev
    Next
    INDEX
    Explanations

    terms related to "excess" or "exceeding" 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 @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.78
    AsUp
    -0.78
     ProtoMessage
    -0.76
    pushFollow
    -0.73
    存于互联网档案馆
    -0.70
     endblock
    -0.67
    IndentedString
    -0.66
     Bewußt
    -0.66
     jsPsych
    -0.65
     Geſch
    -0.65
    POSITIVE LOGITS
     excess
    0.66
     mass
    0.66
     disease
    0.53
     exceeding
    0.53
    mass
    0.51
     holes
    0.50
     ele
    0.49
     several
    0.48
    length
    0.48
     disc
    0.47
    Activations Density 0.196%

    No Known Activations