© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12494
    Prev
    Next
    INDEX
    Explanations

    HTML input fields with placeholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.85
    "]);
    -0.80
    "]);
    -0.76
    ++
    -0.76
    `]
    -0.73
    "])
    -0.72
    twimg
    -0.72
    "])){
    -0.69
     {}));
    -0.69
    '){
    -0.69
    POSITIVE LOGITS
     placeholder
    2.73
    placeholder
    2.57
     Placeholder
    2.11
    Placeholder
    2.04
    PlaceHolder
    1.45
    PLACE
    1.08
    place
    1.04
    holders
    1.04
    HOLDER
    1.03
     place
    0.96
    Activations Density 0.027%

    No Known Activations