© 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. 10-GEMMASCOPE-RES-16K
    11. 6095
    Prev
    Next
    INDEX
    Explanations

    references to the front part of objects, specifically in terms of location or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.50
     Préférences
    -0.48
    樣的
    -0.46
     Zuf
    -0.45
    mazoo
    -0.45
    マイズ
    -0.42
    songwriter
    -0.41
     desigual
    -0.41
     pedas
    -0.41
     useParams
    -0.41
    POSITIVE LOGITS
     front
    2.14
    Front
    1.91
    front
    1.89
     Front
    1.88
     FRONT
    1.81
    FRONT
    1.72
     fronts
    1.39
     frontend
    1.32
     frontline
    1.24
     Frontend
    1.23
    Activations Density 0.117%

    No Known Activations