© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    tentative language or expressions of uncertainty

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

    the word "perhaps" and words that follow it in argumentative or speculative statements.

    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
     apparently
    -0.98
     evidently
    -0.94
     obviously
    -0.90
     presumably
    -0.88
    apparently
    -0.86
    presumably
    -0.83
     clearly
    -0.81
     Apparently
    -0.79
     seemingly
    -0.77
     Clearly
    -0.77
    POSITIVE LOGITS
     someday
    0.75
     algún
    0.72
     algun
    0.62
     subconscious
    0.61
     alguno
    0.60
    ̈́
    0.59
     qualche
    0.58
     alguna
    0.58
    addContainerGap
    0.58
     subconsciously
    0.58
    Activations Density 0.797%

    No Known Activations