© 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. 10-GEMMASCOPE-RES-16K
    11. 6536
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.61
     disambiguazione
    -0.60
    ThroughAttribute
    -0.58
    TintMode
    -0.57
    IsContent
    -0.53
    SourceChecksum
    -0.53
    #+#
    -0.53
    hig
    -0.50
     муніципалі
    -0.50
     jät
    -0.49
    POSITIVE LOGITS
    GeneratedMessage
    0.54
    CloseOperation
    0.50
    깥
    0.50
    AutoScaleMode
    0.48
     doccia
    0.47
     pillow
    0.47
    allax
    0.47
     rope
    0.46
    :`
    0.46
    wydd
    0.45
    Activations Density 0.954%

    No Known Activations