© 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. 23-GEMMASCOPE-RES-16K
    11. 11513
    Prev
    Next
    INDEX
    Explanations

    terms associated with fame and reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.59
     Anſ
    -0.53
    iſh
    -0.52
     Reſ
    -0.52
     Inſ
    -0.50
    anneer
    -0.50
     Pullman
    -0.49
     Perſ
    -0.47
    provision
    -0.47
    illip
    -0.47
    POSITIVE LOGITS
     KNOWN
    1.01
     known
    0.99
     famous
    0.99
     Known
    0.96
    known
    0.91
    KNOWN
    0.89
    famous
    0.88
     Famous
    0.88
    Known
    0.86
    Famous
    0.85
    Activations Density 0.206%

    No Known Activations