© 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. 31-GEMMASCOPE-RES-16K
    11. 12466
    Prev
    Next
    INDEX
    Explanations

    instances of conditional phrases indicating time or causality

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

    the word "When" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.72
     transfieras
    -0.64
    parsedMessage
    -0.63
     AssemblyCulture
    -0.61
    tvguidetime
    -0.60
     ivelany
    -0.60
    WebElementEntity
    -0.60
    +#+
    -0.59
    RefNanny
    -0.59
    rungsseite
    -0.57
    POSITIVE LOGITS
     asked
    0.44
    Πηγές
    0.40
     I
    0.40
     you
    0.40
     a
    0.39
     viewed
    0.37
     successful
    0.37
     sufficiently
    0.37
     Ihnen
    0.35
     interviewed
    0.35
    Activations Density 0.236%

    No Known Activations