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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 9299
    Prev
    Next
    INDEX
    Explanations

    the word "given" and its context in relation to statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normandy
    -0.87
     Normandie
    -0.76
     AppColors
    -0.73
    enumii
    -0.70
    effetto
    -0.70
    صرية
    -0.70
     venons
    -0.67
     tasche
    -0.66
     Pamplona
    -0.66
    Unsubscribe
    -0.66
    POSITIVE LOGITS
     Given
    1.29
     given
    1.22
    Given
    1.16
    given
    1.07
    iven
    1.06
     GIVEN
    0.98
    Dado
    0.96
     Dado
    0.90
     dado
    0.88
    dado
    0.86
    Activations Density 0.136%

    No Known Activations