Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.57
    .
    -0.54
    IsContent
    -0.54
     lượt
    -0.53
    ,
    -0.52
     оригіналу
    -0.51
    !
    -0.51
    ConstraintMaker
    -0.50
     Chwiliwch
    -0.50
    ;
    -0.50
    POSITIVE LOGITS
     HttpNotFound
    0.73
    )*/
    0.67
     """
    
    0.66
    */
    
    0.64
     OMITBAD
    0.64
    '''
    
    0.63
    ();*/
    0.63
     />';
    0.63
     */
    
    0.61
     endregion
    0.60
    Activations Density 0.342%

    No Known Activations