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. 24-GEMMASCOPE-RES-16K
    6. 16344
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the term "Or" in different contexts

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

    "Or" at the beginning of a line

    np_acts-logits-general · gemini-2.0-flash

    detects 'Or' followed by words or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {}{}
    -0.67
    참고
    -0.62
     much
    -0.62
     BytesLike
    -0.59
    much
    -0.58
     незавершена
    -0.56
    Much
    -0.55
    addContainerGap
    -0.54
    mybatisplus
    -0.53
     uParam
    -0.52
    POSITIVE LOGITS
     Мексичка
    0.55
     kaarangay
    0.55
    ']));
    0.52
    parsedMessage
    0.52
    setVerticalGroup
    0.51
    fromnode
    0.51
    IUrlHelper
    0.49
     Exactos
    0.49
     '{@
    0.48
     Dernière
    0.48
    Activations Density 0.141%

    No Known Activations