© 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. 8-GEMMASCOPE-RES-16K
    11. 15202
    Prev
    Next
    INDEX
    Explanations

    situations involving strong emotional or physical reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ™
    -0.47
     associated
    -0.46
     asam
    -0.45
     regional
    -0.45
     {
    -0.44
     worldwide
    -0.43
     research
    -0.43
    യ
    -0.43
     inter
    -0.42
     Prof
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    1.15
    Tikang
    0.99
    awtextra
    0.99
    帖最后由
    0.98
     GenerationType
    0.98
    tagext
    0.96
     >=",
    0.95
    ConstraintMaker
    0.94
    TagHelper
    0.94
    ViewFeatures
    0.93
    Activations Density 0.990%

    No Known Activations