© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    6. 3025
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers related to database operations and queries

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

    Code-related keywords

    np_acts-logits-general · gemini-2.0-flash

    code keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.35
    .
    -0.33
     nantinya
    -0.33
     légitime
    -0.32
     fieltro
    -0.32
    attendre
    -0.31
     ferons
    -0.31
    occasione
    -0.30
     demais
    -0.30
    accesso
    -0.29
    POSITIVE LOGITS
    …).
    0.80
    ...).
    0.77
    "],
    
    0.75
    __*/
    0.74
    ...),
    0.73
    */
    
    
    0.73
    ...".
    0.73
    ValueStyle
    0.71
     **/
    
    0.71
    ...");
    
    0.70
    Activations Density 2.307%

    No Known Activations