© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3301
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or conjecture

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

    guessing or speculation

    np_acts-logits-general · gemini-2.0-flash

    guessing, speculating, or assuming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alvor
    -0.52
    իկ
    -0.50
    antMatchers
    -0.48
     vergeten
    -0.48
    delaire
    -0.47
     jurí
    -0.47
    olarmente
    -0.47
     pério
    -0.47
     néglig
    -0.46
     tardi
    -0.45
    POSITIVE LOGITS
     guesses
    2.19
     guessing
    2.18
     guessed
    2.16
     guess
    2.15
     speculation
    1.95
    guess
    1.91
     conjecture
    1.81
     speculate
    1.76
     Guess
    1.75
     speculating
    1.75
    Activations Density 0.529%

    No Known Activations