© 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. 0-GEMMASCOPE-RES-16K
    11. 11249
    Prev
    Next
    INDEX
    Explanations

    instances of the word "detail" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.58
    
    -0.56
     dagelijks
    -0.49
     gesloten
    -0.46
     zijne
    -0.45
     gouvernements
    -0.45
     juges
    -0.45
    FormTagHelper
    -0.45
    CrossRef
    -0.44
     PopupWindow
    -0.43
    POSITIVE LOGITS
     detail
    1.27
     details
    1.05
     DETAIL
    1.02
    Detail
    0.93
     Detail
    0.91
     Details
    0.89
    detail
    0.87
    Details
    0.84
    details
    0.82
     detalle
    0.81
    Activations Density 0.268%

    No Known Activations