© 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. 7918
    Prev
    Next
    INDEX
    Explanations

    scientific references and figure citations in the text

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

    Tokens immediately preceding a bracketed figure reference

    np_acts-logits-general · gemini-2.0-flash

    figure citation labels

    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
     nahilalakip
    -1.10
    ValueStyle
    -0.86
    IUrlHelper
    -0.79
     BoxDecoration
    -0.78
    migrationBuilder
    -0.69
    merksam
    -0.67
    قایناق‌لار
    -0.66
    XmlAccessorType
    -0.62
    thenReturn
    -0.62
     Pingback
    -0.62
    POSITIVE LOGITS
    –
    0.46
    地
    0.46
    \&
    0.44
    usec
    0.43
    ({},
    0.43
    częściej
    0.43
     Lijst
    0.42
     Arxivat
    0.41
    &
    0.41
     trebui
    0.40
    Activations Density 0.632%

    No Known Activations