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. 10328
    Prev
    Next
    INDEX
    Explanations

    references to shadows and their effects or characteristics

    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
    ptonshire
    -0.65
    />";
    -0.58
     getItemId
    -0.54
    tiko
    -0.52
    زیین
    -0.52
    nals
    -0.51
    FirebaseDatabase
    -0.51
    usepackage
    -0.49
     Spontaneous
    -0.49
     Waltham
    -0.49
    POSITIVE LOGITS
     shade
    1.36
    shade
    1.30
     shades
    1.29
     Shade
    1.29
    Shade
    1.23
     Shades
    1.22
     darkness
    1.19
     shading
    1.13
     shadows
    1.11
     curtain
    1.11
    Activations Density 0.281%

    No Known Activations