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. 10179
    Prev
    Next
    INDEX
    Explanations

    specific structural or formatting elements in academic or technical writing, particularly those related to mathematical expressions and citations

    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
     Ouverture
    -0.68
    ACHUSET
    -0.64
     betweenstory
    -0.61
    ătate
    -0.60
    homonymie
    -0.59
     GetEnumerator
    -0.58
    ImageField
    -0.58
    DeleteBehavior
    -0.57
    affaires
    -0.56
     metropolitana
    -0.55
    POSITIVE LOGITS
    󠁢
    0.66
    >--}}
    0.61
    __*/
    0.59
     nahilalakip
    0.59
    )$_
    0.56
    ValueStyle
    0.56
    assi
    0.54
    بوابة
    0.54
     Heid
    0.54
     lenker
    0.53
    Activations Density 0.239%

    No Known Activations