© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11850
    Prev
    Next
    INDEX
    Explanations

    descriptions of financial constraints or difficulties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rąg
    -0.35
     mérito
    -0.30
    latego
    -0.30
    GIVEREF
    -0.30
    _));
    -0.30
     nowo
    -0.29
    一句话
    -0.29
     впервые
    -0.28
    CheckedChanged
    -0.28
    不過
    -0.28
    POSITIVE LOGITS
     sufficient
    1.23
     adequate
    1.21
     enough
    1.09
    Sufficient
    1.07
    sufficient
    1.04
     voldoende
    1.02
     Sufficient
    1.01
    enough
    1.01
     genügend
    1.00
     Adequate
    0.98
    Activations Density 0.742%

    No Known Activations