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. 17-GEMMASCOPE-RES-16K
    6. 1179
    Prev
    Next
    INDEX
    Explanations

    certain types of brackets and their placement, particularly in relation to figures and captions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iprot
    -0.68
    σθαι
    -0.64
     BorderRadius
    -0.61
    CardContent
    -0.61
     neer
    -0.60
     المعيارى
    -0.58
     createSprite
    -0.58
    mybatisplus
    -0.57
    PullParser
    -0.57
    AllAfrica
    -0.56
    POSITIVE LOGITS
     "..\..\..\
    0.80
     @"/
    0.72
    ✨:
    0.71
    ]{
    0.68
    ῷ
    0.65
     Beller
    0.64
     للاسماء
    0.63
    ++){
    0.62
     "..\..\
    0.62
    AccessorTable
    0.61
    Activations Density 0.101%

    No Known Activations