© 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. 15252
    Prev
    Next
    INDEX
    Explanations

    media entities such as songs, artists, and albums

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

    Content within quotation marks or parentheses

    np_acts-logits-general · gemini-2.0-flash

    song titles and times

    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
    ^(@)
    -1.22
     itſelf
    -1.14
    .",
    -1.12
    .")
    -1.12
    !")
    -1.09
    ?
    -1.02
    $")
    -1.01
    ".
    -1.00
    !
    -1.00
    */;
    -0.99
    POSITIVE LOGITS
     &
    1.11
     -
    1.07
     –
    0.96
     +
    0.93
     /
    0.93
     featuring
    0.84
     (
    0.78
     vs
    0.73
     @
    0.69
     feat
    0.69
    Activations Density 0.373%

    No Known Activations