© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 7166
    Prev
    Next
    INDEX
    Explanations

    structural elements related to coding or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ?
    -0.55
    ?
    -0.52
    <b>
    -0.48
    PyErr
    -0.45
     
    -0.45
     bes
    -0.44
     kotlin
    -0.44
    nap
    -0.42
    <
    -0.42
     GenerationType
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.92
    tvguidetime
    0.87
     فريبيس
    0.78
    findpost
    0.76
     ویکی‌پدی
    0.74
     disambiguazione
    0.74
     Italijanski
    0.73
    исленность
    0.72
     nakalista
    0.71
     Савезне
    0.71
    Activations Density 0.031%

    No Known Activations