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. 4530
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Well"

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

    Follows the word "Well"

    np_acts-logits-general · gemini-2.0-flash

    well, to be fair

    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
     industriale
    -0.63
     religieuses
    -0.60
    nonatomic
    -0.60
     viktigt
    -0.59
     jsPsych
    -0.56
     daarvan
    -0.54
    Programming
    -0.54
    fører
    -0.53
     eorum
    -0.52
     heti
    -0.52
    POSITIVE LOGITS
     done
    0.87
     Done
    0.79
     aware
    0.63
     worth
    0.63
     actually
    0.62
     versed
    0.62
     known
    0.62
    come
    0.62
     deserved
    0.62
     played
    0.61
    Activations Density 0.050%

    No Known Activations