© 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. 15-GEMMASCOPE-RES-16K
    11. 3928
    Prev
    Next
    INDEX
    Explanations

    reasons or explanations for actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inoue
    -0.51
     dök
    -0.44
     online
    -0.41
     at
    -0.38
     Münster
    -0.38
     kült
    -0.38
    ndash
    -0.37
     McKay
    -0.36
    IMC
    -0.36
    :✨
    -0.36
    POSITIVE LOGITS
     Reason
    1.49
     reason
    1.48
    Reason
    1.38
     reasons
    1.38
     Reasons
    1.35
     REASON
    1.33
    REASON
    1.27
    reason
    1.26
    Reasons
    1.24
     REASONS
    1.21
    Activations Density 0.138%

    No Known Activations