© 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. 35-GEMMASCOPE-RES-16K
    11. 5024
    Prev
    Next
    INDEX
    Explanations

    terms related to ethical and legal aspects of research documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.54
     totiž
    -0.49
     Menschheit
    -0.47
     więc
    -0.42
     있으며
    -0.41
     eikä
    -0.40
     podjet
    -0.40
    ล้ว
    -0.39
    humanité
    -0.38
    이며
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.79
    </h3>
    0.77
    StructEnd
    0.74
     propOrder
    0.73
     kaarangay
    0.73
    MessageOf
    0.73
    </h4>
    0.72
    contentLoaded
    0.71
    EndGlobalSection
    0.71
     Wikimedijinoj
    0.71
    Activations Density 1.105%

    No Known Activations