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. 2-GEMMASCOPE-RES-16K
    6. 4385
    Prev
    Next
    INDEX
    Explanations

    questions and answers related to inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.80
     chande
    -0.72
    NameInMap
    -0.70
    Cordialement
    -0.68
    LikeLike
    -0.68
    ,:),
    -0.67
    ,:);
    -0.67
    AnimationsModule
    -0.67
     autorytatywna
    -0.67
    makeConstraints
    -0.67
    POSITIVE LOGITS
    rest
    0.55
    IElement
    0.53
     brief
    0.52
    pulumi
    0.48
    reactstrap
    0.48
    ives
    0.47
     />\
    0.47
    ap
    0.47
    ent
    0.47
     Talis
    0.47
    Activations Density 0.139%

    No Known Activations