© 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. 13755
    Prev
    Next
    INDEX
    Explanations

    references to knowledge, understanding, or insights regarding specific subjects

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

    phrases containing "to our knowledge" or similar expressions of epistemic stance about information gaps.

    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
     سكانية
    -0.57
    sizeCache
    -0.56
     RISERVATA
    -0.56
    JsonFormat
    -0.53
    ftagPool
    -0.52
     المعيارى
    -0.52
    省市镇
    -0.50
    webElement
    -0.49
    UserScript
    -0.48
    tiérrez
    -0.48
    POSITIVE LOGITS
     extent
    0.66
     detriment
    0.61
    extent
    0.49
     accompaniment
    0.45
    为止
    0.44
     ול
    0.44
     liking
    0.43
     tune
    0.43
     hilt
    0.40
     aid
    0.39
    Activations Density 0.286%

    No Known Activations