© 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. 4-GEMMASCOPE-RES-16K
    6. 12689
    Prev
    Next
    INDEX
    Explanations

    references to code structures or components, likely related to programming or software architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.94
    ValueStyle
    -0.85
    EndContext
    -0.78
     insuffisamment
    -0.75
     AppColors
    -0.70
    abetes
    -0.70
    脚注の使い方
    -0.69
    rungsseite
    -0.68
    ніципа
    -0.68
    verwijspagina
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.78
    omitempty
    0.60
     Dro
    0.59
    qtype
    0.57
     himo
    0.55
    Datuak
    0.53
    </table>
    0.50
     Riti
    0.50
    Dro
    0.49
     amantes
    0.48
    Activations Density 0.245%

    No Known Activations