© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6096
    Prev
    Next
    INDEX
    Explanations

    references to the term "front" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
     escolar
    -0.88
    MeasureSpec
    -0.87
    ASUS
    -0.80
     judiciaire
    -0.79
     culturelles
    -0.78
    ukone
    -0.78
    Jody
    -0.78
     religieuses
    -0.77
    TintMode
    -0.76
    styrelsen
    -0.76
    POSITIVE LOGITS
     front
    1.68
     FRONT
    1.60
     Front
    1.60
    front
    1.55
    Front
    1.52
    FRONT
    1.40
     fron
    1.23
     Fron
    1.18
     fronts
    1.16
    Fron
    1.16
    Activations Density 0.049%

    No Known Activations