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

    Neuronpedia

    APICircuit 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. 22-GEMMASCOPE-RES-16K
    6. 14005
    Prev
    Next
    INDEX
    Explanations

    various concepts related to health, community support, and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     והוא
    -1.21
    ConstraintMaker
    -1.16
    이고
    -1.09
    featureID
    -1.08
    rungsseite
    -1.08
    曖昧さ回避
    -1.03
    findpost
    -1.01
    tvguidetime
    -0.95
    homonymie
    -0.94
    脚注の使い方
    -0.94
    POSITIVE LOGITS
    /
    1.02
     accordingly
    0.80
     thereafter
    0.78
     serta
    0.77
    -/
    0.75
     respectively
    0.73
     therefrom
    0.70
     /
    0.69
     thereon
    0.64
    /
    0.63
    Activations Density 1.263%

    No Known Activations