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

    Neuronpedia

    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. 4-GEMMASCOPE-RES-16K
    11. 2151
    Prev
    Next
    INDEX
    Explanations

    terms related to hyperplanes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.66
    Cyfeiriadau
    -0.59
    parsedMessage
    -0.59
    당
    -0.58
     ProtoMessage
    -0.58
    Anmerkungen
    -0.57
    ComponentModel
    -0.56
    IsMutable
    -0.56
    Tikang
    -0.53
     Insee
    -0.52
    POSITIVE LOGITS
     surface
    1.25
     plane
    1.18
     surfaces
    1.15
    surface
    1.14
    surfaces
    1.11
     Surface
    1.07
     SURFACE
    1.05
     PLANE
    1.04
    plane
    1.02
     Surfaces
    1.01
    Activations Density 0.953%

    No Known Activations