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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 2451
    Prev
    Next
    INDEX
    Explanations

    phrases related to classifications and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anskje
    -0.76
    олові
    -0.76
    Життєпис
    -0.75
    RenderAtEndOf
    -0.72
    archiviato
    -0.72
    richTextPanel
    -0.70
    ArgumentParser
    -0.70
    yakarta
    -0.67
     الرياضيه
    -0.66
    postIndex
    -0.65
    POSITIVE LOGITS
     titled
    0.69
     labeled
    0.67
     Horowitz
    0.67
    :
    0.61
     Planet
    0.60
     saying
    0.59
     lautet
    0.59
     “
    0.59
     Kraus
    0.59
    HasColumnType
    0.59
    Activations Density 0.450%

    No Known Activations