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. 2420
    Prev
    Next
    INDEX
    Explanations

    key concepts related to philosophical thinking and critical analysis

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

    preceding alternatives/exceptions (e.g., "but", "rather")

    np_acts-logits-general · gemini-2.0-flash

    but

    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
    Yet
    -0.99
     Yet
    -0.98
     Pourtant
    -0.95
     yet
    -0.87
     entanto
    -0.78
     pourtant
    -0.77
    yet
    -0.73
     OFDb
    -0.68
     cependant
    -0.67
    PositiveButton
    -0.66
    POSITIVE LOGITS
     sondern
    1.81
     بلکه
    1.54
     אלא
    1.48
    而是
    1.42
     sino
    1.40
     melainkan
    1.37
     hanem
    1.30
     vaan
    1.29
     utan
    1.15
     nor
    1.12
    Activations Density 0.194%

    No Known Activations