© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    names and references related to individuals named Steve, Stephen, or Steven

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

    proper names, particularly first names of people.

    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
     protoimpl
    -0.63
    IntoConstraints
    -0.61
    IBOutlet
    -0.58
    kháu
    -0.41
    parsedMessage
    -0.40
     Roskov
    -0.38
    ConstraintMaker
    -0.37
    UrlResolution
    -0.37
    featureID
    -0.36
    EndInit
    -0.35
    POSITIVE LOGITS
    
    0.51
    出版年
    0.50
    liceerd
    0.50
    PLANATION
    0.49
     Steve
    0.49
     Jobs
    0.46
    Steve
    0.46
    WEBPACK
    0.45
    lewati
    0.44
     Spielberg
    0.44
    Activations Density 0.099%

    No Known Activations