© 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. 9328
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or behaviors associated with leadership or performance

    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
     nahilalakip
    -0.81
     GenerationType
    -0.72
    ftagPool
    -0.67
    ReusableCell
    -0.67
    enderror
    -0.58
    ViewFeatures
    -0.58
    rtype
    -0.58
     externi
    -0.58
     sterili
    -0.56
    KURZBESCHREIBUNG
    -0.54
    POSITIVE LOGITS
     acts
    0.80
     Acts
    0.75
    uate
    0.74
     ACT
    0.72
    acts
    0.68
    uation
    0.65
     act
    0.65
     acted
    0.63
    ACT
    0.60
     acto
    0.59
    Activations Density 0.078%

    No Known Activations