© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5556
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or conjecture in reasoning

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

    speculative or conjectural language, particularly phrases expressing guessing, assumptions, or uncertain reasoning.

    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
    tisseur
    -0.31
     Kriterien
    -0.29
     enfrenta
    -0.28
     realities
    -0.28
    occasione
    -0.27
    esistenza
    -0.27
     dargestellt
    -0.27
    徑
    -0.26
     Interessen
    -0.26
    lichten
    -0.26
    POSITIVE LOGITS
     guess
    3.09
     guesses
    2.72
    guess
    2.72
     Guess
    2.70
    Guess
    2.63
     guessing
    2.63
     guessed
    2.56
    猜
    1.93
    guesses
    1.91
    猜测
    1.84
    Activations Density 0.420%

    No Known Activations