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. 20-GEMMASCOPE-RES-131K
    6. 70649
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     OMITTED
    -0.42
    Ārējās
    -0.42
     Abou
    -0.39
     Houſe
    -0.39
    uré
    -0.38
    ONTO
    -0.38
    XmlAccessorType
    -0.37
     disambiguazione
    -0.37
     fles
    -0.35
     Specific
    -0.35
    POSITIVE LOGITS
    
    0.63
    IsMutable
    0.50
    principalColumn
    0.48
     '{@
    0.47
     transfieras
    0.46
    Gambas
    0.44
     "..\..\
    0.44
    Werdegang
    0.43
    EndProject
    0.43
    keyColumn
    0.43
    Activations Density 0.141%

    No Known Activations