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. 5-GEMMASCOPE-RES-16K
    6. 7555
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -1.10
    elemField
    -1.01
     utafitiHapana
    -1.00
    GraphicsUnit
    -1.00
     oprot
    -0.95
     defaultstate
    -0.95
    kloped
    -0.94
     متعلقه
    -0.93
    +#+
    -0.92
     فريبيس
    -0.91
    POSITIVE LOGITS
    ↵↵
    0.78
    ++]=
    0.54
    Joachim
    0.49
    彝
    0.49
    <eos>
    0.48
    icina
    0.48
    ')}}">
    0.48
     "
    0.46
     -
    0.45
     cut
    0.45
    Activations Density 0.083%

    No Known Activations