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. 10-GEMMASCOPE-RES-16K
    6. 15801
    Prev
    Next
    INDEX
    Explanations

    various HTML and user interface elements related to form fields and labels

    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
     Paglinawan
    -0.68
    nodoc
    -0.62
    ```
    -0.61
     ]];
    -0.60
     onCreate
    -0.60
    skap
    -0.56
    '],
    
    -0.56
    శ
    -0.56
    Læs
    -0.56
    ```
    
    -0.55
    POSITIVE LOGITS
     _('
    0.75
    }{*}{
    0.71
     dolayı
    0.70
    <td>
    0.70
     industriel
    0.68
     degrés
    0.66
     ouvriers
    0.64
     _("
    0.63
     étoient
    0.63
     parlent
    0.62
    Activations Density 0.150%

    No Known Activations