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. 13-GEMMASCOPE-RES-16K
    6. 9628
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the preposition indicating inclusion or location (being within or part of something), especially marking a state of being.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biologique
    -0.64
     neuve
    -0.62
     mẽ
    -0.58
    unggulan
    -0.56
     تعدى
    -0.55
    田市
    -0.55
    DNEY
    -0.54
     chrétien
    -0.54
     virginity
    -0.53
     africain
    -0.53
    POSITIVE LOGITS
    InputBorder
    0.79
    queryInterface
    0.74
     position
    0.70
     reached
    0.70
    "]];
    0.68
    Bronnen
    0.68
     able
    0.67
    parsedMessage
    0.67
    SceneManagement
    0.64
     done
    0.64
    Activations Density 0.180%

    No Known Activations