© 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. 3-GEMMASCOPE-RES-16K
    6. 10335
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or keywords related to coding and software development

    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
     cherchez
    -0.48
     
    -0.46
     रहे
    -0.44
     lẫn
    -0.43
    })()
    -0.43
    getItemId
    -0.43
    言い
    -0.40
     say
    -0.40
     Hütte
    -0.40
     Inner
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    1.21
    Portail
    0.93
    ########.
    0.93
    Geplaatst
    0.91
    Hozzáférés
    0.86
     uVar
    0.86
    DrawerToggle
    0.85
    脚注の使い方
    0.84
    ArrowToggle
    0.84
     فريبيس
    0.83
    Activations Density 1.017%

    No Known Activations