© 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. 3-GEMMASCOPE-RES-16K
    11. 6096
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or terms associated with places or local entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.39
     Administrativna
    -0.38
    الدراسه
    -0.35
    FillColor
    -0.34
    jgl
    -0.34
    __':
    -0.34
     nahilalakip
    -0.33
     Autorisations
    -0.32
    fxml
    -0.31
    ittäin
    -0.31
    POSITIVE LOGITS
    Dun
    1.56
     Dun
    1.54
     dun
    1.48
    Bun
    1.47
     Bun
    1.44
     Kun
    1.41
     Hun
    1.39
    Kun
    1.38
    bun
    1.34
    UN
    1.32
    Activations Density 0.538%

    No Known Activations