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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16142
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Connecticut and its specific locations or institutions

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

    Connecticut and Yale

    np_acts-logits-general · gemini-2.0-flash

    Connecticut, Yale, Debian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flügel
    -0.33
    inquirer
    -0.33
    LikeLike
    -0.32
    AnimationsModule
    -0.32
     pleaſure
    -0.31
    ArgumentParser
    -0.30
    ประ
    -0.30
    Erwin
    -0.29
     Vögel
    -0.28
    lotl
    -0.28
    POSITIVE LOGITS
     Westport
    0.78
    Autoritní
    0.68
     Norwalk
    0.66
    Personendaten
    0.66
     Bridgeport
    0.66
     Fairfield
    0.64
    XMLSchema
    0.59
     Taunton
    0.58
    UnusedPrivate
    0.58
    :✨
    0.58
    Activations Density 0.082%

    No Known Activations