Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129947
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "cleavage" or "cleaved" in various contexts

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

    cleave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verbund
    -0.36
     Total
    -0.35
     Dord
    -0.35
     failing
    -0.34
    strix
    -0.34
     Harg
    -0.33
     amo
    -0.33
    ToString
    -0.33
    Portály
    -0.33
     Horse
    -0.33
    POSITIVE LOGITS
    Cle
    0.88
     Cle
    0.86
     cle
    0.75
     CLE
    0.71
    CLE
    0.68
     cleave
    0.66
    cleared
    0.66
     ब्रेकडाउन
    0.66
    cle
    0.65
     cleavage
    0.61
    Activations Density 0.010%

    No Known Activations