© 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. 2-GEMMASCOPE-RES-16K
    11. 8630
    Prev
    Next
    INDEX
    Explanations

    evidence of claims, suggestions, or indicators in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.54
     Stays
    -0.53
    neous
    -0.52
    expandindo
    -0.52
     eats
    -0.52
     tors
    -0.52
    Faces
    -0.51
    abit
    -0.50
     GLFW
    -0.49
     ModelRenderer
    -0.49
    POSITIVE LOGITS
     suggests
    1.77
     indicates
    1.66
    indicates
    1.37
     implies
    1.36
     explains
    1.35
     sugiere
    1.21
     confirms
    1.20
     Indicates
    1.17
     demonstrates
    1.13
     illustrates
    1.13
    Activations Density 0.236%

    No Known Activations