© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11896
    Prev
    Next
    INDEX
    Explanations

    terms related to significant statistical analysis and prognosis in data

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

    preceding parenthetical citations

    np_acts-logits-general · gemini-2.0-flash

    listing items respectively

    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
    pylene
    -0.47
    ')";
    -0.45
    isNaN
    -0.44
    //{
    -0.43
    󠁢
    -0.43
    isert
    -0.42
    Література
    -0.42
    entet
    -0.41
    }{$\
    -0.41
    パール
    -0.41
    POSITIVE LOGITS
     respectively
    0.71
     begge
    0.66
     respectivamente
    0.60
    respectively
    0.59
    这两个
    0.58
     ambos
    0.58
     respectivement
    0.57
     beiden
    0.55
     båda
    0.54
    どちらも
    0.53
    Activations Density 1.300%

    No Known Activations