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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14575
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or possibility expressed with the word "might."

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

    Sentences containing "might" or "might be"

    np_acts-logits-general · gemini-2.0-flash

    might followed by verbs

    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
    er
    -0.76
    ear
    -0.67
     Breen
    -0.65
    asteroide
    -0.59
    ER
    -0.57
    CardHeader
    -0.57
    তথ্যসূত্র
    -0.56
    dır
    -0.56
     ECA
    -0.55
    cektir
    -0.55
    POSITIVE LOGITS
     MIGHT
    0.86
    ally
    0.85
     conceivably
    0.82
    chitis
    0.79
    might
    0.79
    esseract
    0.78
    Moi
    0.78
     might
    0.76
    ————————
    0.76
    Might
    0.73
    Activations Density 0.055%

    No Known Activations