© 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. 3-GEMMASCOPE-RES-16K
    11. 1085
    Prev
    Next
    INDEX
    Explanations

    references to short durations or brief instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.86
     AssemblyVersion
    -0.77
     Réponses
    -0.68
    FormTagHelper
    -0.67
    GEBURTSDATUM
    -0.66
    %)$
    -0.66
    panou
    -0.65
    DidLoad
    -0.65
     referenties
    -0.64
    odeon
    -0.64
    POSITIVE LOGITS
     short
    3.60
     Short
    3.42
    Short
    3.39
     SHORT
    3.30
    short
    3.23
    SHORT
    3.01
    短
    2.40
     shorter
    2.28
     Shorts
    2.25
     shorts
    2.24
    Activations Density 0.074%

    No Known Activations