© 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. 20-GEMMASCOPE-RES-16K
    6. 6118
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and system operations

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

    hexadecimal or machine-level programming code identifiers and commands.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    occurrences of the letter t/T, especially as a final consonant cluster or short token ending in t.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the letter sequence "t" in technical or code-related contexts, particularly in variable names, function names, and abbreviations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >
    
    
    -0.60
     clearColor
    -0.57
     userName
    -0.56
    ható
    -0.55
     stockbild
    -0.54
    Coordenadas
    -0.54
    ‗
    -0.53
     columnName
    -0.53
    %)$
    -0.52
    iern
    -0.51
    POSITIVE LOGITS
    tt
    0.89
    t
    0.85
    ttt
    0.82
    tttt
    0.81
    tet
    0.78
    at
    0.73
    test
    0.72
    zt
    0.70
    lt
    0.69
    ty
    0.69
    Activations Density 1.797%

    No Known Activations