© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15297
    Prev
    Next
    INDEX
    Explanations

    snippets of code or programming constructs

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

    Code-related terms and file extensions

    np_acts-logits-general · gemini-2.0-flash

    code and UI elements

    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
     more
    -1.70
    more
    -1.37
    More
    -1.27
     More
    -1.18
     mehr
    -1.09
     MORE
    -1.04
     más
    -0.98
     более
    -0.95
     lebih
    -0.94
     více
    -0.94
    POSITIVE LOGITS
    ModelAdmin
    0.90
    UnknownFields
    0.88
    GraphicsUnit
    0.86
    StoryboardSegue
    0.86
     AssemblyProduct
    0.84
    RectangleBorder
    0.79
    tvguidetime
    0.77
     تضيفلها
    0.75
    Tikang
    0.75
    ScopeManager
    0.74
    Activations Density 0.109%

    No Known Activations