© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 9908
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions related to calculations

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

    ± standard deviation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     queſta
    -0.98
     ſind
    -0.81
     صوتيه
    -0.80
    parsedMessage
    -0.79
    majánló
    -0.76
     '\\;'
    -0.72
    Personendaten
    -0.71
    MLLoader
    -0.71
     bookId
    -0.71
    RenderAtEndOf
    -0.70
    POSITIVE LOGITS
     מל
    0.51
     وك
    0.48
     וב
    0.45
     כשה
    0.42
    =
    0.41
     כש
    0.40
    — 
    0.40
    @
    0.39
     ول
    0.39
     Weihnachts
    0.39
    Activations Density 0.618%

    No Known Activations