© 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. 28-GEMMASCOPE-RES-16K
    11. 6970
    Prev
    Next
    INDEX
    Explanations

    suggestions for tools and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before adjectives describing suitability or goodness

    np_acts-logits-general · gemini-2.0-flash

    suitable/appropriate evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essentiel
    -0.37
     enää
    -0.35
    näm
    -0.35
     näm
    -0.34
     zaji
    -0.33
    unlike
    -0.32
     hoppas
    -0.32
    saraba
    -0.32
    principalTable
    -0.32
     necesariamente
    -0.32
    POSITIVE LOGITS
     suitable
    0.94
     appropriate
    0.86
     good
    0.85
    suitable
    0.81
    Suitable
    0.80
     Suitable
    0.77
     Appropriate
    0.77
     подходя
    0.77
     useful
    0.75
     excellent
    0.74
    Activations Density 0.452%

    No Known Activations