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. 122685
    Prev
    Next
    INDEX
    Explanations

    themes related to family dynamics and emotional struggles

    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
     actualidad
    -0.43
    سطس
    -0.43
    libft
    -0.42
    getItemId
    -0.40
     Verfahrens
    -0.40
    ximately
    -0.40
    tagez
    -0.38
     brigades
    -0.38
    iniums
    -0.38
     Durée
    -0.38
    POSITIVE LOGITS
     kaarangay
    0.62
    mybatisplus
    0.62
     ModelExpression
    0.56
    RegistryLite
    0.49
    Déc
    0.47
    Jereo
    0.46
    reactstrap
    0.43
     Chwiliwch
    0.43
    طقة
    0.42
    gonic
    0.41
    Activations Density 0.047%

    No Known Activations