© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 749
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting in texts, particularly lists and organizational features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.83
    sizeCache
    -0.82
    :✨
    -0.80
    Попис
    -0.78
     betweenstory
    -0.77
     resourceCulture
    -0.76
     snippetHide
    -0.75
    出版年
    -0.75
    expandindo
    -0.73
     utafitiHapana
    -0.73
    POSITIVE LOGITS
    <strong>
    2.58
    <b>
    2.13
    <u>
    1.16
    <em>
    1.13
     
    1.13
    <i>
    1.04
    <code>
    0.98
     **
    0.82
    <sup>
    0.68
    mathbf
    0.68
    Activations Density 1.349%

    No Known Activations