© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15427
    Prev
    Next
    INDEX
    Explanations

    code structure elements, particularly method declarations and their syntax in programming

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

    Code delimiters and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -1.09
    "],
    -0.98
    `,
    -0.96
    __':
    -0.95
    __":
    -0.94
    ',
    -0.91
    ."],
    -0.91
    ]")]
    -0.87
    '],
    -0.85
    "])
    -0.84
    POSITIVE LOGITS
    .
    0.40
     contactez
    0.35
    ↵
    0.34
     informé
    0.32
     destinées
    0.31
     inginkan
    0.31
     supplémentaire
    0.31
    </tr>
    0.30
     informativo
    0.30
     supérieurs
    0.30
    Activations Density 0.399%

    No Known Activations