© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5244
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, particularly those involving symbols and operations in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     صوتيه
    -0.61
     EconPapers
    -0.58
    endpush
    -0.56
    RTEX
    -0.54
    IntoConstraints
    -0.53
     myſelf
    -0.53
    TagMode
    -0.53
    RTCF
    -0.52
    extAlignment
    -0.52
    EndContext
    -0.51
    POSITIVE LOGITS
     장
    0.35
     establecido
    0.34
     pener
    0.33
     perdidos
    0.30
     Branchen
    0.30
     battre
    0.30
     őket
    0.30
    pēc
    0.29
     perdiendo
    0.29
     established
    0.29
    Activations Density 2.446%

    No Known Activations