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. 21-GEMMASCOPE-RES-16K
    6. 8378
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface states and data rendering in a React component

    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
     Jefus
    -0.74
     ་་
    -0.73
    TargetException
    -0.68
    CloseOperation
    -0.67
    ########.
    -0.67
     Reſ
    -0.65
     myſelf
    -0.65
    ſelves
    -0.62
     Monfieur
    -0.62
    :✨
    -0.62
    POSITIVE LOGITS
     <
    1.07
    <>
    0.87
    <
    0.84
     <>
    0.84
    <tr>
    0.70
    ={<
    0.61
    ><
    0.59
    ↵
    0.58
    (<
    0.56
    :<
    0.54
    Activations Density 0.031%

    No Known Activations