© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    references to formats and formatting functions

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

    "format" followed by ":" or properties

    np_acts-logits-general · gemini-2.0-flash

    formatters or format

    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
     calculées
    -0.78
    sizeCache
    -0.74
     cref
    -0.68
    AnchorTagHelper
    -0.67
     numberWith
    -0.64
     numberOfRows
    -0.63
    protoimpl
    -0.63
     GenerationType
    -0.62
     GetEnumerator
    -0.61
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
    ters
    0.82
     formats
    0.71
    dehyde
    0.70
     FORMAT
    0.69
    bootstrapcdn
    0.66
     bax
    0.66
    tings
    0.64
     iParam
    0.63
    tazione
    0.62
    setSource
    0.62
    Activations Density 0.093%

    No Known Activations