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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 14484
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical concepts, including expressions and sequences

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

    Mathematical/scientific notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    premeditated

    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
    GEBURTSDATUM
    -0.31
    Anhalt
    -0.30
    endregion
    -0.30
     Temporada
    -0.30
    permitAll
    -0.29
    couragement
    -0.29
    compiler
    -0.28
    ttemberg
    -0.28
     recomendada
    -0.27
    contentLoaded
    -0.27
    POSITIVE LOGITS
    ьаж
    0.66
    SequentialGroup
    0.59
     ModelExpression
    0.59
    MLLoader
    0.56
    Ƚ
    0.55
    IsContent
    0.53
     QtWidgets
    0.52
    Tembelea
    0.52
    الحياه
    0.51
     anyway
    0.50
    Activations Density 2.313%

    No Known Activations