© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3214
    Prev
    Next
    INDEX
    Explanations

    attributes and settings related to assembly metadata in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.79
     …..
    -0.78
    MENAFN
    -0.73
    RegressionTest
    -0.70
    ?’
    -0.69
     Roskov
    -0.69
    …..
    -0.68
    oredCriteria
    -0.67
     ….
    -0.67
    ErrorListener
    -0.66
    POSITIVE LOGITS
    <unused62>
    0.69
    <unused61>
    0.66
    <unused63>
    0.64
    .*/
    0.61
     */
    0.59
    .
    
    0.56
    <unused60>
    0.55
     {@
    0.54
    .</
    0.53
    .");
    0.52
    Activations Density 0.175%

    No Known Activations