© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5027
    Prev
    Next
    INDEX
    Explanations

    variable declarations and access modifiers (private, public) in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     autorytatywna
    -1.30
     ویکی‌پدی
    -1.24
     Италијани
    -1.20
     queſta
    -1.09
     zwiſchen
    -1.04
    ſſung
    -1.04
    Vidite
    -1.02
     ſeinen
    -1.02
     témoig
    -1.01
    <unused3>
    -1.00
    POSITIVE LOGITS
    ↵
    0.50
    <strong>
    0.38
    _
    0.37
    ,
    0.34
     
    0.33
    .
    0.32
    /
    0.32
    <h2>
    0.30
     the
    0.28
    From
    0.28
    Activations Density 0.254%

    No Known Activations