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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15487
    Prev
    Next
    INDEX
    Explanations

    instances of specific formatting or patterns in labeled data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageInfo
    -0.58
    DataContract
    -0.57
    ServletConfig
    -0.54
    soni
    -0.52
    CopyWith
    -0.52
    EDEFAULT
    -0.52
    colat
    -0.51
    Étymologie
    -0.51
    +#+
    -0.50
    DataAdapter
    -0.50
    POSITIVE LOGITS
     дописавши
    0.84
    \{\\
    0.73
    انيف
    0.69
     متعلقه
    0.68
    ंदीखरीदारी
    0.66
    */;
    0.66
     **/
    0.65
     ***!
    0.64
    .")]
    0.64
    TagMode
    0.64
    Activations Density 0.061%

    No Known Activations