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. 53868
    Prev
    Next
    INDEX
    Explanations

    the word "additional" and its variations

    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
     pageContext
    -0.63
     Italijani
    -0.59
    ArgsConstructor
    -0.57
     IBOutlet
    -0.53
    charCode
    -0.53
     ​​
    -0.53
     Suivez
    -0.52
    bateria
    -0.52
     Administrativna
    -0.52
    curve
    -0.51
    POSITIVE LOGITS
     additional
    1.28
    additional
    1.09
     Additional
    1.09
    Additional
    1.05
     ADDITIONAL
    0.95
    ADDITIONAL
    0.92
     addition
    0.91
    vábbi
    0.82
     zusätzlichen
    0.81
     추가
    0.79
    Activations Density 0.032%

    No Known Activations