© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1404
    Prev
    Next
    INDEX
    Explanations

    numbers, identifiers, and statistical data

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

    References citing journal, volume, and page number

    np_acts-logits-general · gemini-2.0-flash

    academic journal volume numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    хьтан
    -0.57
     kasarigan
    -0.50
     AssemblyCulture
    -0.48
     nakalista
    -0.48
     bod
    -0.42
     bot
    -0.41
     مرئيه
    -0.39
     Prom
    -0.39
     noble
    -0.38
     wet
    -0.38
    POSITIVE LOGITS
     zoude
    0.52
    MemoryWarning
    0.52
    SBATCH
    0.47
     noemen
    0.46
     Walkover
    0.44
     Obrador
    0.44
    ؤلاء
    0.43
     dezelve
    0.43
     krwi
    0.42
     pamamagitan
    0.42
    Activations Density 0.608%

    No Known Activations