© 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. 6207
    Prev
    Next
    INDEX
    Explanations

    terms related to procedural steps and systematic reviews in scientific research

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

    Results, yields, or produces something

    np_acts-logits-general · gemini-2.0-flash

    producing or yielding results

    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
     ControllerBase
    -0.87
    EDEFAULT
    -0.64
    antino
    -0.61
    EndInit
    -0.58
     AssemblyTitle
    -0.58
    ériques
    -0.56
     mapStateToProps
    -0.53
    ArgsConstructor
    -0.53
    ureusement
    -0.52
    lidene
    -0.52
    POSITIVE LOGITS
     produces
    1.99
     produce
    1.94
     yielding
    1.93
     yields
    1.91
     yield
    1.87
     producing
    1.86
     yielded
    1.80
    yield
    1.76
     resulted
    1.68
    produce
    1.68
    Activations Density 1.912%

    No Known Activations