© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 16015
    Prev
    Next
    INDEX
    Explanations

    details related to properties and possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warren
    -0.37
     Ti
    -0.35
     final
    -0.35
     temp
    -0.34
    Warren
    -0.33
     equilibrium
    -0.32
     부
    -0.32
     WARREN
    -0.32
    InSeconds
    -0.31
     code
    -0.30
    POSITIVE LOGITS
     apparently
    0.85
     Apparently
    0.78
    apparently
    0.77
     evidently
    0.76
     presumably
    0.75
     Presumably
    0.73
     AssemblyCulture
    0.70
    Apparently
    0.69
     Evidently
    0.69
     probably
    0.68
    Activations Density 0.904%

    No Known Activations