© 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. 3-GEMMASCOPE-RES-16K
    11. 7730
    Prev
    Next
    INDEX
    Explanations

    terms related to conveying information or messages

    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
     Hopf
    -0.71
    XtraEditors
    -0.68
     Chrift
    -0.68
    NSNotification
    -0.67
    stdio
    -0.66
     cowardice
    -0.66
    queryInterface
    -0.65
    WebVitals
    -0.64
     Britann
    -0.61
     demurrer
    -0.61
    POSITIVE LOGITS
     convey
    1.64
     conveys
    1.52
     conveyed
    1.45
     conveying
    1.40
     Convey
    1.35
    Convey
    1.26
     artic
    1.19
     portray
    1.13
     articulate
    1.10
     portrays
    1.02
    Activations Density 0.232%

    No Known Activations