© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10688
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with historical and controversial subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    +#+#
    -0.68
     nahilalakip
    -0.65
     Chwiliwch
    -0.65
     resourceCulture
    -0.65
    دانشنامهٔ
    -0.63
     propOrder
    -0.63
    DockStyle
    -0.60
    Hentet
    -0.60
     հղումներ
    -0.59
    principalTable
    -0.59
    POSITIVE LOGITS
     SG
    0.38
     DG
    0.38
    iser
    0.37
    sales
    0.35
     @
    0.35
     Segu
    0.35
     spacer
    0.35
     sales
    0.34
     moderator
    0.34
     Sales
    0.33
    Activations Density 0.170%

    No Known Activations