© 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. 82
    Prev
    Next
    INDEX
    Explanations

    code constructs related to counting and index manipulation

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

    Code or program snippets

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    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
    Спољашње
    -0.61
    ">//
    -0.60
    Chham
    -0.59
     AssemblyTitle
    -0.58
     resourceCulture
    -0.54
    Extinguishing
    -0.53
    PrintStream
    -0.52
    InstrumentedTest
    -0.50
     linkovi
    -0.50
    ঔ
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.95
    PerformLayout
    0.82
    EndContext
    0.79
    enumi
    0.68
    AndEndTag
    0.68
     BoxFit
    0.67
    RUnlock
    0.66
    DockStyle
    0.65
    awtextra
    0.63
    IntoConstraints
    0.61
    Activations Density 0.084%

    No Known Activations