© 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. 844
    Prev
    Next
    INDEX
    Explanations

    references to statistical concepts or results related to estimators and their properties

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

    other works using an "@" symbol

    np_acts-logits-general · gemini-2.0-flash

    citation parentheses or brackets

    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
     '\\;'
    -0.64
    IndentedString
    -0.61
     ModelExpression
    -0.60
    ůměr
    -0.58
    kuuta
    -0.57
     оригіналу
    -0.57
    IBOutlet
    -0.55
    fromnode
    -0.54
    UnusedPrivate
    -0.53
    iNdEx
    -0.52
    POSITIVE LOGITS
    providedIn
    0.54
     ostavi
    0.53
    SPECIFIED
    0.53
     stessi
    0.51
     cyclisme
    0.51
    helves
    0.50
     minimization
    0.50
    homonymie
    0.50
    ;">
    0.49
    otropy
    0.49
    Activations Density 0.168%

    No Known Activations