© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 465
    Prev
    Next
    INDEX
    Explanations

    elements related to concepts, entities, and mathematical functions within discussions of complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zieży
    -0.51
     is
    -0.47
    dsi
    -0.47
    idist
    -0.45
    다고
    -0.45
    <eos>
    -0.44
    ánd
    -0.43
     under
    -0.43
    jön
    -0.42
     outdoors
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.97
     AspNetCore
    0.81
    :✨
    0.79
     withal
    0.76
    GEBURTSDATUM
    0.74
     kasarigan
    0.72
    出版年
    0.71
     Administrativna
    0.71
    évaluateur
    0.70
    الإنجليزية
    0.69
    Activations Density 1.291%

    No Known Activations