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. 20-GEMMASCOPE-RES-16K
    6. 12703
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of conjecture and speculation

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

    guessing or speculating

    np_acts-logits-general · gemini-2.0-flash

    guessing and speculating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SafeAreaView
    -0.42
     gigi
    -0.39
    ftance
    -0.39
     aprobó
    -0.36
     taşı
    -0.36
    getDisplay
    -0.36
     Diener
    -0.36
    mbals
    -0.35
    쁠
    -0.35
    体现
    -0.35
    POSITIVE LOGITS
     guesses
    0.90
     guess
    0.85
     guessing
    0.84
     suspect
    0.83
     guessed
    0.82
     suspicion
    0.78
    guess
    0.75
     conjecture
    0.73
     inferences
    0.72
     conjectures
    0.72
    Activations Density 0.788%

    No Known Activations