© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4324
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and parameters related to physical experiments

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

    Mathematical and scientific notation

    np_acts-logits-general · gemini-2.0-flash

    symbols and "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
     <<<<<<<<<<<<<<
    -0.65
    ftagPool
    -0.65
    :][
    -0.62
    UnusedPrivate
    -0.61
    majánló
    -0.60
    :✨
    -0.59
     oprot
    -0.56
    Ārējās
    -0.56
    帖最后由
    -0.56
     leſs
    -0.56
    POSITIVE LOGITS
    HostException
    0.35
    Clik
    0.33
    ILING
    0.32
     respective
    0.31
     referirse
    0.30
    bcryptjs
    0.30
     الن
    0.29
     overwhelmed
    0.28
     overshadowed
    0.28
     kı
    0.28
    Activations Density 0.966%

    No Known Activations