© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 7591
    Prev
    Next
    INDEX
    Explanations

    citations and metadata related to scientific articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.65
     (
    -0.62
     in
    -0.61
     
    -0.60
     di
    -0.59
    ,
    -0.58
     D
    -0.57
     V
    -0.55
     f
    -0.54
     of
    -0.52
    POSITIVE LOGITS
     للمعارف
    1.32
    WindowConstants
    1.23
    ConstraintMaker
    1.14
     createSlice
    1.08
     GenerationType
    1.08
    IntoConstraints
    1.06
     contextLoads
    1.05
     MainAxisSize
    1.04
     Efq
    1.04
     crdi
    1.01
    Activations Density 0.478%

    No Known Activations