© 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. 33-GEMMASCOPE-RES-16K
    11. 6331
    Prev
    Next
    INDEX
    Explanations

    examples and hypothetical scenarios in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tramonto
    -0.49
    UnsafeEnabled
    -0.48
     myös
    -0.47
     ayrıca
    -0.47
     definitivamente
    -0.45
     solcher
    -0.44
     lisäksi
    -0.43
     solches
    -0.43
     także
    -0.42
     pungkas
    -0.42
    POSITIVE LOGITS
     suppose
    1.78
     Suppose
    1.69
     imagine
    1.63
    Suppose
    1.62
     assume
    1.48
     Imagine
    1.45
    Imagine
    1.45
     Assume
    1.38
    Assume
    1.36
    imagine
    1.30
    Activations Density 0.820%

    No Known Activations