© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    references to academic or scholarly works

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

    references to academic qualifications and scholarly work

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

    titles and headings

    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
    DIPSETTING
    -0.52
    CodeDom
    -0.52
     spéciales
    -0.50
    __(/*!
    -0.50
     unknownFields
    -0.49
    erialization
    -0.48
     CreateTagHelper
    -0.48
     }}"></
    -0.47
    awtextra
    -0.46
     CallOverrides
    -0.46
    POSITIVE LOGITS
     title
    3.40
    title
    2.87
     Title
    2.85
     titles
    2.76
    Title
    2.69
     TITLE
    2.60
     título
    2.49
    TITLE
    2.44
     titel
    2.39
     titolo
    2.34
    Activations Density 0.350%

    No Known Activations