© 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. 8236
    Prev
    Next
    INDEX
    Explanations

    Python import statements and initialization of libraries

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

    Lines ending with a period

    np_acts-logits-general · gemini-2.0-flash

    python programming code

    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
    ranje
    -0.46
    неопр
    -0.43
    ofern
    -0.42
    stery
    -0.42
     posses
    -0.41
    grà
    -0.41
    ————————
    -0.41
    utz
    -0.40
    pany
    -0.40
    Vind
    -0.40
    POSITIVE LOGITS
    ########.
    0.79
     nakalista
    0.67
     समीक्षाओं
    0.60
    enderror
    0.59
    epy
    0.58
    RenderAtEndOf
    0.57
    RUnlock
    0.56
     "..\..\
    0.56
     فريبيس
    0.55
     ευ
    0.55
    Activations Density 0.106%

    No Known Activations