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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1002
    Prev
    Next
    INDEX
    Explanations

    phrases related to contracts and agreements, particularly in a professional or sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    a time period or agreement

    np_acts-logits-general · gemini-2.0-flash

    duration of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.40
    Prompt
    -0.37
     مرئيه
    -0.36
     sarung
    -0.35
    辍
    -0.35
     يتيمه
    -0.34
     berge
    -0.34
     Tobin
    -0.33
     coti
    -0.33
     defaultstate
    -0.33
    POSITIVE LOGITS
     duration
    0.87
     lasts
    0.85
     Duration
    0.83
     lasting
    0.82
     duración
    0.79
     durata
    0.78
     durée
    0.76
     jangka
    0.76
    duration
    0.75
     durations
    0.71
    Activations Density 0.336%

    No Known Activations