© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 38630
    Prev
    Next
    INDEX
    Explanations

    elements related to the timeline and structure of projects or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.39
     lagi
    -0.37
    بوابة
    -0.37
    わけ
    -0.35
    CrossRef
    -0.34
     funny
    -0.34
    #+#
    -0.34
     trừ
    -0.34
     lại
    -0.33
    ny
    -0.33
    POSITIVE LOGITS
     itſelf
    0.84
    TagMode
    0.82
    脚注の使い方
    0.78
     himſelf
    0.78
    يميديا
    0.77
     myſelf
    0.74
     firſt
    0.72
     first
    0.72
    ₁)
    0.71
     Première
    0.71
    Activations Density 0.050%

    No Known Activations