© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3915
    Prev
    Next
    INDEX
    Explanations

    information related to genetic variations and their statistical analysis

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

    followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    are, were, would, or that

    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
    RTLR
    -0.47
    Autoritní
    -0.43
     plazos
    -0.42
     greateſt
    -0.38
    IBOutlet
    -0.37
    ngOnDestroy
    -0.37
     Majefty
    -0.37
     horario
    -0.36
     auprès
    -0.36
    ientras
    -0.35
    POSITIVE LOGITS
    prepareStatement
    0.50
    новништво
    0.45
     have
    0.44
    GOTREF
    0.43
    ienki
    0.42
    canestro
    0.42
    pting
    0.42
    पया
    0.42
     actively
    0.41
    تقاوى
    0.40
    Activations Density 0.563%

    No Known Activations