© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15282
    Prev
    Next
    INDEX
    Explanations

    statistical thresholds and criteria related to data analysis and interpretation

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

    statistical thresholds and comparison expressions (like "greater than," "higher than," or values exceeding certain cutoffs).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     autorytatywna
    -0.79
    UserScript
    -0.77
     poffible
    -0.63
    ########.
    -0.61
     houſe
    -0.61
    AsUp
    -0.60
     fubject
    -0.59
    KURZBESCHREIBUNG
    -0.58
     AssemblyProduct
    -0.58
     Houſe
    -0.54
    POSITIVE LOGITS
    CreateIndex
    0.38
    Viitteet
    0.36
     scores
    0.36
     deviation
    0.35
     poor
    0.35
     signals
    0.35
     gap
    0.34
     signal
    0.34
     negative
    0.34
     lack
    0.32
    Activations Density 0.472%

    No Known Activations