© 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. 3-GEMMASCOPE-RES-16K
    11. 6459
    Prev
    Next
    INDEX
    Explanations

    blocks of code or script-like structures within programming context

    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
     Hickman
    -0.87
     Herak
    -0.86
    FAK
    -0.85
     HomeComponent
    -0.85
     LEAR
    -0.83
     Seneca
    -0.83
     Haarlem
    -0.82
    äsenti
    -0.82
     lear
    -0.82
     Rajan
    -0.82
    POSITIVE LOGITS
                     
    1.53
                         
    1.29
             
    1.11
                             
    0.93
    0.80
         
    0.80
    {{--
    0.78
     ạ
    0.76
    ing
    0.71
    いる
    0.68
    Activations Density 0.098%

    No Known Activations