© 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. 18-GEMMASCOPE-RES-16K
    11. 3976
    Prev
    Next
    INDEX
    Explanations

    references to plots or schematics in a narrative or analytical context

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

    Text related to plots or plotting

    np_acts-logits-general · gemini-2.0-flash

    plot and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.78
    addPreferredGap
    -0.69
     Dede
    -0.66
    ReusableCell
    -0.63
     يتيمه
    -0.61
    IsMutable
    -0.60
     Италијани
    -0.60
     Vive
    -0.59
     Shand
    -0.59
    fjspx
    -0.58
    POSITIVE LOGITS
     Plots
    1.03
     PLOT
    1.01
     plots
    1.00
     Plot
    0.95
     plot
    0.95
    PLOT
    0.89
    Plots
    0.83
    plot
    0.82
    plots
    0.79
     Plo
    0.79
    Activations Density 0.158%

    No Known Activations