© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 655
    Prev
    Next
    INDEX
    Explanations

    the presence of markers indicating structural components or elements in a system

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

    the start of a new document or section

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

    alternatives or otherwise

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    PreferredItem
    -0.83
    enumi
    -0.80
     propOrder
    -0.64
     Derfor
    -0.63
    الإنجليزية
    -0.60
     ErrIntOverflow
    -0.58
     hence
    -0.55
     Jeder
    -0.55
    GTCX
    -0.55
    そりゃ
    -0.54
    POSITIVE LOGITS
     Alternatively
    1.09
    Alternatively
    0.98
     alternatively
    0.98
    Altern
    0.92
     Altern
    0.89
    altern
    0.82
     Remember
    0.79
    Otherwise
    0.76
     Otherwise
    0.76
     alternativ
    0.75
    Activations Density 0.048%

    No Known Activations