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

    Neuronpedia

    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. 10475
    Prev
    Next
    INDEX
    Explanations

    structural elements typical in programming languages, such as brackets and specific formatting symbols

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

    Code snippets or data structures

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses and braces

    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
    IsMutable
    -0.84
     Normdatei
    -0.82
    ⟬
    -0.82
     يتيمه
    -0.82
     للمعارف
    -0.79
    <unused41>
    -0.77
    <pad>
    -0.77
    <unused28>
    -0.77
    [@BOS@]
    -0.76
    <unused8>
    -0.76
    POSITIVE LOGITS
    mær
    0.37
     begge
    0.36
     respectivement
    0.34
     nø
    0.31
     chrétien
    0.29
     skjø
    0.29
     muchacha
    0.29
     båda
    0.28
     sabid
    0.28
     respectivamente
    0.28
    Activations Density 1.019%

    No Known Activations