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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4621
    Prev
    Next
    INDEX
    Explanations

    relationships and insights related to scientific studies and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PhysRev
    -0.68
    djangoproject
    -0.61
    SPATH
    -0.58
     Вікіпе
    -0.56
    oog
    -0.56
    TintMode
    -0.55
    EDEFAULT
    -0.55
    handleRequest
    -0.55
    SearchParams
    -0.52
    RegressionTest
    -0.51
    POSITIVE LOGITS
     revealing
    1.27
     reveal
    1.20
     provide
    1.15
     reveals
    1.14
     provides
    1.12
    reve
    1.11
     helps
    1.11
     sheds
    1.10
     shed
    1.10
     help
    1.04
    Activations Density 0.912%

    No Known Activations