© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and investigations

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

    "We" followed by a verb of investigation or analysis

    np_acts-logits-general · gemini-2.0-flash

    we examine / investigate

    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
    dropIfExists
    -0.78
    abestanden
    -0.76
    enumi
    -0.68
    ngOnInit
    -0.66
    ViewFeatures
    -0.64
     noqa
    -0.60
    Obrázky
    -0.60
     diciendo
    -0.60
     dikatakan
    -0.58
     spirituale
    -0.57
    POSITIVE LOGITS
     compared
    0.72
     examined
    0.68
     compare
    0.65
     investigated
    0.64
     tested
    0.63
     evaluated
    0.62
     assessed
    0.60
     measure
    0.58
    compared
    0.57
    tagHelperRunner
    0.56
    Activations Density 1.339%

    No Known Activations