© 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. 38-GEMMASCOPE-RES-16K
    11. 16140
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations and incidents of violence or unrest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comfort
    -0.39
    Comfort
    -0.38
     Comfort
    -0.38
     otomatig
    -0.35
     COMFORT
    -0.33
     Tet
    -0.32
    ковь
    -0.32
    comfort
    -0.31
     Boli
    -0.30
    PAP
    -0.30
    POSITIVE LOGITS
     Somalia
    1.05
    Somalia
    0.99
     Somali
    0.99
    Som
    0.91
     Somaliland
    0.91
     Som
    0.84
     Somal
    0.84
     Punt
    0.82
     som
    0.76
    som
    0.71
    Activations Density 0.134%

    No Known Activations