© 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. 24-GEMMASCOPE-RES-16K
    11. 12511
    Prev
    Next
    INDEX
    Explanations

    mentions of guidance, support services, and community-related terms

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

    Following certain short words

    np_acts-logits-general · gemini-2.0-flash

    conclusions, Arizona, evident, history, inquiry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     câte
    -0.87
     picioare
    -0.87
     piele
    -0.78
     înal
    -0.76
     gând
    -0.74
     stră
    -0.73
     maș
    -0.72
     noastre
    -0.71
     îna
    -0.69
     obicei
    -0.69
    POSITIVE LOGITS
     dur
    0.82
     whe
    0.79
     wit
    0.76
     wh
    0.76
     кото
    0.75
     wi
    0.75
     fr
    0.71
     recenti
    0.70
     espec
    0.70
     towar
    0.69
    Activations Density 0.815%

    No Known Activations