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. 15933
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain connecting phrases

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

    Followed by "I" or punctuation

    np_acts-logits-general · gemini-2.0-flash

    starts of sentences after punctuation

    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
     queſta
    -0.84
    RTGC
    -0.84
     geſch
    -0.81
     vooz
    -0.79
     Geiſt
    -0.79
     Taktlose
    -0.79
    ðsíða
    -0.78
     dieſen
    -0.78
    BeginInit
    -0.77
     verſch
    -0.77
    POSITIVE LOGITS
     I
    0.76
    I
    0.65
    Hope
    0.64
     Hope
    0.62
     Seems
    0.57
     hope
    0.56
    hope
    0.56
    Seems
    0.54
    Gotta
    0.50
    Just
    0.50
    Activations Density 0.463%

    No Known Activations