© 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. 13082
    Prev
    Next
    INDEX
    Explanations

    references to models, designs, or components in technical or product-related contexts

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

    Followed by "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    is buckled or cyclical

    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
     AttributeSet
    -0.65
    bited
    -0.46
    glEnd
    -0.46
    ghijkl
    -0.44
    ofluor
    -0.41
    kfree
    -0.41
     Did
    -0.41
    encodeWith
    -0.41
    egl
    -0.40
    inkin
    -0.40
    POSITIVE LOGITS
     is
    1.60
    ValueStyle
    1.04
     are
    0.98
    帖最后由
    0.93
     là
    0.89
     είναι
    0.89
    IsContent
    0.85
    is
    0.83
     IS
    0.81
     isComment
    0.81
    Activations Density 0.250%

    No Known Activations