© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 9794
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "cum" and its variations in different contexts

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

    cum, cumulative, or Cummins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     langage
    -0.39
     Händen
    -0.38
     noires
    -0.37
     ſtate
    -0.36
     ſtre
    -0.36
     précédentes
    -0.35
     délai
    -0.35
     laſt
    -0.35
     pleaſure
    -0.35
     mengapa
    -0.34
    POSITIVE LOGITS
     cum
    2.61
    Cum
    2.47
     Cum
    2.45
    cum
    2.42
     CUM
    2.02
    CUM
    1.86
     Cummins
    1.60
     cumul
    1.41
     Cumming
    1.34
     cumulative
    1.30
    Activations Density 0.006%

    No Known Activations