Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 14354
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms, particularly related to geographical locations and entities

    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
    olites
    -0.52
    sphase
    -0.50
    sstelle
    -0.49
    skir
    -0.47
    paravant
    -0.47
     která
    -0.47
     spokeswoman
    -0.46
     casque
    -0.45
    Odkazy
    -0.45
    enerys
    -0.45
    POSITIVE LOGITS
    +#+#
    0.57
    Portail
    0.55
    __((
    0.53
     '\\;'
    0.51
    ")){
    0.50
    нгредіє
    0.49
    crawl
    0.49
    WebElementEntity
    0.48
    SequentialGroup
    0.48
     Almond
    0.47
    Activations Density 0.034%

    No Known Activations