Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13915
    Prev
    Next
    INDEX
    Explanations

    significant legal terms and references

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

    Numbers within surrounding text

    np_acts-logits-general · gemini-2.0-flash

    numbers and asterisks

    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
    RectangleBorder
    -0.75
    expandindo
    -0.71
    ſſung
    -0.67
     zwiſchen
    -0.66
     ſeine
    -0.64
     estekak
    -0.63
    BibitemShut
    -0.63
     myſelf
    -0.62
     queſta
    -0.62
     ſche
    -0.62
    POSITIVE LOGITS
    最快更新
    0.37
    outState
    0.35
    iostream
    0.35
    mintaan
    0.35
    ('../
    0.33
     defaultstate
    0.33
    生
    0.32
     merupakan
    0.32
    The
    0.32
    This
    0.31
    Activations Density 0.273%

    No Known Activations