© 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. 22-GEMMASCOPE-RES-16K
    11. 5744
    Prev
    Next
    INDEX
    Explanations

    structured programming syntax or code-related constructs

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

    Code snippets with namespaces

    np_acts-logits-general · gemini-2.0-flash

    C# class declarations

    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
    SequentialGroup
    -0.73
    ANDUM
    -0.56
     Hift
    -0.52
    basicConfig
    -0.51
     itſelf
    -0.51
     Sver
    -0.50
    IDAS
    -0.49
     ftre
    -0.48
    ſelves
    -0.48
     ſind
    -0.48
    POSITIVE LOGITS
     виправивши
    0.96
    AnchorStyles
    0.65
     bezeichneter
    0.63
    Tembelea
    0.62
    migrationBuilder
    0.62
    adpleegd
    0.57
    enterOuterAlt
    0.57
    StructEnd
    0.57
    Abit
    0.55
    cshtml
    0.55
    Activations Density 0.089%

    No Known Activations