© 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. 39-GEMMASCOPE-RES-16K
    6. 552
    Prev
    Next
    INDEX
    Explanations

    metadata and structural information in code or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (')
    -0.56
    ([]
    -0.49
    ('.'
    -0.46
     Mel
    -0.44
    uría
    -0.44
    httphttps
    -0.43
    OMP
    -0.42
    Mel
    -0.41
    '''
    -0.41
    )"),
    -0.41
    POSITIVE LOGITS
    ']>;
    0.52
     HttpNotFound
    0.47
    "]();
    0.47
    "}";
    0.47
    NameInMap
    0.47
     OGSÅ
    0.42
    AlterField
    0.42
    queryInterface
    0.40
     TextInputType
    0.40
    |};
    0.39
    Activations Density 0.388%

    No Known Activations