© 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. 15-GEMMASCOPE-RES-16K
    11. 4707
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions used in equations

    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
    енча
    -0.53
     ***!
    -0.50
    hdysval
    -0.47
    ésie
    -0.45
    })`
    -0.44
    '])){
    -0.44
     Bourke
    -0.43
     lenker
    -0.42
    trzy
    -0.42
     Stadium
    -0.41
    POSITIVE LOGITS
    PasswordEncoder
    0.68
     صوتيه
    0.68
    rizona
    0.65
    featureID
    0.65
    ClientSize
    0.64
     Lightboxes
    0.62
     laikā
    0.56
     mergeFrom
    0.55
    ArgumentParser
    0.54
    žius
    0.54
    Activations Density 1.006%

    No Known Activations