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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10760
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and frankness in opinions or statements

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

    Adverbs that express an opinion

    np_acts-logits-general · gemini-2.0-flash

    expressing honest opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.66
    SourceChecksum
    -0.59
     propOrder
    -0.57
    drawSprites
    -0.56
    Rüyada
    -0.54
     يتيمه
    -0.54
     autorytatywna
    -0.54
    pædia
    -0.51
    ğraf
    -0.50
     ویکی‌آمباردا
    -0.50
    POSITIVE LOGITS
     frankly
    0.75
     honestly
    0.72
    Frankly
    0.67
     Honestly
    0.64
    Honestly
    0.63
    honestly
    0.61
     tbh
    0.53
     eigenlijk
    0.48
     eigentlich
    0.47
    Actually
    0.47
    Activations Density 0.325%

    No Known Activations