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

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-16K
    11. 2338
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or temporal qualifiers in discussions

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

    "sometimes"

    np_acts-logits-general · gemini-2.0-flash

    the word sometimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.48
     pleaſure
    -0.44
     ſche
    -0.44
     implication
    -0.41
     quæ
    -0.38
    trend
    -0.36
    ราย
    -0.36
     Concer
    -0.36
     viñ
    -0.36
     implications
    -0.36
    POSITIVE LOGITS
     sometimes
    1.83
     Sometimes
    1.73
    sometimes
    1.70
    Sometimes
    1.70
     occasionally
    1.45
     manchmal
    1.40
     Occasionally
    1.38
     kadang
    1.37
     parfois
    1.34
     иногда
    1.34
    Activations Density 0.159%

    No Known Activations