© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 278
    Prev
    Next
    INDEX
    Explanations

    nested brackets or multi-level notations

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

    bracketed references and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '],$
    -0.41
    }}^
    -0.40
    '}}
    -0.39
    .}}
    -0.38
    *
    -0.38
    "}},
    -0.38
    >")
    -0.37
    }}}\
    -0.36
    }</
    -0.36
     *
    -0.36
    POSITIVE LOGITS
    【
    1.04
     【
    0.97
    、【
    0.87
    ：【
    0.80
    $_['
    0.68
    請繼續往下閱讀
    0.66
     [
    0.61
     regrettable
    0.60
    　　【
    0.59
     Helga
    0.59
    Activations Density 0.011%

    No Known Activations