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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7138
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.65
    """.
    -0.59
    "%(
    -0.57
    ̍t
    -0.56
    /*
    -0.55
     ویکی‌آمباردا
    -0.53
    ‴
    -0.52
    DrawerToggle
    -0.52
     соответственно
    -0.51
     typelib
    -0.50
    POSITIVE LOGITS
     فإن
    0.77
     though
    0.68
    +:+
    0.65
    HtmlAttribute
    0.65
    onViewCreated
    0.64
    ;
    0.64
    :
    0.57
     ***!
    0.56
     when
    0.56
    一句
    0.56
    Activations Density 0.265%

    No Known Activations