© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 70239
    Prev
    Next
    INDEX
    Explanations

    terms related to "cleave" or "cleavage" processes in biological contexts

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

    words starting with cle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.63
    bootstrapcdn
    -0.60
     otomatig
    -0.60
    లాలు
    -0.60
    ItemBackground
    -0.60
    
    -0.58
    tanleria
    -0.54
    dafx
    -0.53
    PYX
    -0.53
    पया
    -0.50
    POSITIVE LOGITS
    Cle
    1.00
     Cle
    0.98
     CLE
    0.85
    CLE
    0.78
     cle
    0.76
    cle
    0.76
     Clemens
    0.75
     Clemson
    0.73
     Clemente
    0.68
     Clé
    0.68
    Activations Density 0.014%

    No Known Activations