© 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. 20-GEMMASCOPE-RES-16K
    11. 105
    Prev
    Next
    INDEX
    Explanations

    structured data and coding syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or unusual symbols

    np_acts-logits-general · gemini-2.0-flash

    code structure `cur:`, `region:`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extrait
    -0.53
     nostru
    -0.53
     său
    -0.52
     quæ
    -0.51
     tantum
    -0.51
     xmm
    -0.50
     Venise
    -0.50
     exacer
    -0.50
     годов
    -0.49
    orianCalendar
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.80
    },{
    0.65
     виправивши
    0.62
    $:
    0.59
    providedIn
    0.57
     MonoBehaviour
    0.55
    [`
    0.55
    帖最后由
    0.55
     $:
    0.54
    }:{
    0.54
    Activations Density 0.192%

    No Known Activations