© 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. 22-GEMMASCOPE-RES-16K
    11. 9035
    Prev
    Next
    INDEX
    Explanations

    terms related to endings or conclusions in various contexts

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

    The token "End" or "end"

    np_acts-logits-general · gemini-2.0-flash

    end words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.91
     ModelExpression
    -0.72
    WillAppear
    -0.68
    photobucket
    -0.67
    HtmlAttribute
    -0.66
    Revenir
    -0.65
     HasFactory
    -0.65
    Bibliographie
    -0.64
     AssemblyCulture
    -0.63
    httphttps
    -0.62
    POSITIVE LOGITS
     End
    0.66
    orses
    0.66
     result
    0.63
    othermic
    0.62
    urable
    0.58
    angers
    0.58
    ANGER
    0.58
    orse
    0.57
     END
    0.57
     cùng
    0.57
    Activations Density 0.168%

    No Known Activations