© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8401
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cut" and its variations, indicating discussions related to cutting or reducing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    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
    -0.42
    ophys
    -0.40
     Шта
    -0.35
    SEGU
    -0.35
    REFER
    -0.35
    mpo
    -0.34
    enswert
    -0.34
    cipline
    -0.34
    isation
    -0.34
    vantaged
    -0.34
    POSITIVE LOGITS
     Cut
    1.07
     cut
    1.06
    Cut
    1.04
    Cutting
    1.03
     CUT
    1.03
     Cutting
    1.02
    cut
    0.99
     cuts
    0.99
     cutting
    0.97
    Cuts
    0.96
    Activations Density 0.152%

    No Known Activations