© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    occurrences of study-related terms and their variations

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

    technical or code-related syntax and database schema elements.

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

    technical metadata keywords and flags—especially null/absence markers, global/state directives, and study/source labels—within code-, table-, or log-like text.

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

    line breaks or newlines in structured technical data such as code, databases, logs, or tabular formats.

    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
     queſta
    -1.12
     snippetHide
    -1.02
     surla
    -0.98
     kasarigan
    -0.94
     незавершена
    -0.91
     kaarangay
    -0.90
    Personendaten
    -0.90
    ésultats
    -0.90
     utafitiHapana
    -0.89
    تقاوى
    -0.88
    POSITIVE LOGITS
    .
    0.77
    ↵↵
    0.71
    ;
    0.67
     also
    0.60
    ↵
    0.59
    );
    0.59
    ).
    0.53
    ,
    0.52
    )
    0.50
    :
    0.49
    Activations Density 0.391%

    No Known Activations