© 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. 14164
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cut" and its variations in context related to reducing or severing

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

    the phrase "cut off" or related phrases involving the word "cut" followed by words indicating separation, removal, or discontinuation.

    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
    retweeted
    -0.39
    REFER
    -0.38
    isation
    -0.38
     reason
    -0.38
    enswert
    -0.37
    SEGU
    -0.34
    PRET
    -0.34
    ização
    -0.34
    hing
    -0.33
    ization
    -0.33
    POSITIVE LOGITS
     cut
    1.20
     Cut
    1.17
    Cut
    1.16
     CUT
    1.13
    cut
    1.13
     Cutting
    1.12
    Cutting
    1.12
    Cuts
    1.08
     cutting
    1.06
     cuts
    1.05
    Activations Density 0.136%

    No Known Activations