© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11466
    Prev
    Next
    INDEX
    Explanations

    code snippets that include structured data handling and error checking

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

    Code block closures

    np_acts-logits-general · gemini-2.0-flash

    closing brace followed by else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.79
     ddelweddau
    -0.79
    tagHelperRunner
    -0.77
    StructEnd
    -0.77
     oprot
    -0.76
     kasarigan
    -0.69
     GenerationType
    -0.67
     оригіналу
    -0.67
     Infórmanos
    -0.66
    {{/
    -0.65
    POSITIVE LOGITS
    RenderAtEndOf
    0.49
    defer
    0.49
    fmt
    0.47
     deras
    0.47
    DeleteMapping
    0.45
    PendingIntent
    0.45
     '\''
    0.45
    سكرية
    0.44
     vs
    0.43
     _,
    0.42
    Activations Density 0.080%

    No Known Activations