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. 2677
    Prev
    Next
    INDEX
    Explanations

    terms related to changes or modifications in states or conditions

    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
     she
    -0.60
    leta
    -0.54
    setInt
    -0.54
    //
    -0.54
    BARA
    -0.53
    uke
    -0.53
     G
    -0.53
    ByExample
    -0.52
    stry
    -0.51
    alous
    -0.51
    POSITIVE LOGITS
     Wikispecies
    0.68
     Autorizaciones
    0.61
    ніципа
    0.61
     utafitiHapana
    0.60
     becauſe
    0.60
    YMMV
    0.58
     Normdatei
    0.58
     itſelf
    0.57
    InputBorder
    0.57
     Akismet
    0.56
    Activations Density 0.477%

    No Known Activations