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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3352
    Prev
    Next
    INDEX
    Explanations

    phrases related to enabling and eliminating restrictions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Egli
    -0.58
     døde
    -0.58
     økonom
    -0.58
     marinho
    -0.57
     TAMBÉM
    -0.56
     politiet
    -0.55
     ansatte
    -0.55
     nostrils
    -0.55
     Puoi
    -0.54
     spørsmål
    -0.54
    POSITIVE LOGITS
    |}{}
    0.52
    >");
    
    0.47
    lägen
    0.46
    }")
    
    0.45
    例文帳に追加
    0.44
    र्न
    0.43
    >';
    
    0.43
    >";
    
    0.43
    Palmar
    0.43
    >'+
    0.43
    Activations Density 0.014%

    No Known Activations