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. 6725
    Prev
    Next
    INDEX
    Explanations

    references to specific biblical verses and chapters

    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
    achal
    -0.49
    ledo
    -0.46
    able
    -0.46
    gesteld
    -0.45
    っちゃ
    -0.41
    ле
    -0.41
    }}^{(
    -0.41
    ريف
    -0.41
    ogra
    -0.41
    اند
    -0.41
    POSITIVE LOGITS
     MainAxisSize
    0.92
     BoxFit
    0.92
    +#+#
    0.92
     متعلقه
    0.88
     Мексичка
    0.87
     BitmapFactory
    0.79
     HasFactory
    0.79
    makeConstraints
    0.76
    脚注の使い方
    0.76
    @[+][
    0.72
    Activations Density 0.187%

    No Known Activations