© 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. 798
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the conclusion or termination of a discussion

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

    "end"

    np_acts-logits-general · gemini-2.0-flash

    end up

    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
     Roskov
    -0.74
    UserScript
    -0.72
    Bibliographie
    -0.71
     DataTypes
    -0.70
     ModelExpression
    -0.68
    WillAppear
    -0.67
     ContentValues
    -0.67
     defStyle
    -0.67
    хьтан
    -0.65
     useStyles
    -0.65
    POSITIVE LOGITS
     End
    0.71
    orses
    0.69
     END
    0.69
    angers
    0.67
    ANGER
    0.65
    owing
    0.60
    othermic
    0.58
    End
    0.57
    urable
    0.57
     end
    0.57
    Activations Density 0.177%

    No Known Activations