Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6841
    Prev
    Next
    INDEX
    Explanations

    mentions of guests 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.84
     الحره
    -0.84
     незавершена
    -0.84
    TintMode
    -0.76
    itigation
    -0.73
     ReactDOM
    -0.72
    ïsme
    -0.70
     DialogInterface
    -0.70
     Retailer
    -0.69
    openqa
    -0.69
    POSITIVE LOGITS
     Guest
    1.43
     guest
    1.42
    Guest
    1.40
    guest
    1.28
     GUEST
    1.08
    GUEST
    0.98
     gues
    0.74
     Guests
    0.68
     convidados
    0.67
    Guests
    0.64
    Activations Density 0.101%

    No Known Activations