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. 24-GEMMASCOPE-RES-16K
    6. 13837
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to court rulings and case outcomes

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

    preceding "despite" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    enduring while facing challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.85
    contentLoaded
    -0.76
    adpleegd
    -0.69
    argout
    -0.66
    MigrationBuilder
    -0.59
    而已
    -0.57
    følgelig
    -0.56
    [];
    
    -0.54
     oprot
    -0.53
    "])
    
    -0.52
    POSITIVE LOGITS
     despite
    3.10
    despite
    2.76
     even
    2.53
     nonostante
    2.46
     spite
    2.43
     malgré
    2.27
     apesar
    2.25
     Despite
    2.24
    even
    2.18
     pesar
    2.14
    Activations Density 0.617%

    No Known Activations