© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 693
    Prev
    Next
    INDEX
    Explanations

    references to visual representations, such as figures and diagrams, within the text

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

    references to figures and diagrams in academic texts

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

    prepositions before figure references

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     shown
    -0.67
     Shown
    -0.58
     listed
    -0.58
    Shown
    -0.55
     pictured
    -0.55
    shown
    -0.54
     mentioned
    -0.53
    Pictured
    -0.50
     indicated
    -0.49
     seen
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.88
     bezeichneter
    0.84
     kasarigan
    0.80
     Figure
    0.80
    tableFuture
    0.76
     tartalomajánló
    0.75
    ScopeManager
    0.73
     FIGURE
    0.72
     Figur
    0.72
     Fig
    0.71
    Activations Density 0.303%

    No Known Activations