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. 18-GEMMASCOPE-RES-16K
    6. 10541
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to GUI (graphical user interface) design or layouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulumi
    -0.57
     okuyayım
    -0.57
     SIMBAD
    -0.56
    جستارهای
    -0.54
     Masyarakat
    -0.53
     potuto
    -0.51
    osex
    -0.51
     móc
    -0.50
     aloud
    -0.49
     tovább
    -0.48
    POSITIVE LOGITS
    Point
    0.78
     ExecuteAsync
    0.73
    point
    0.69
     point
    0.68
     Point
    0.67
     consultato
    0.64
     POINT
    0.63
    getPoint
    0.59
    EndProject
    0.59
     createSlice
    0.58
    Activations Density 0.006%

    No Known Activations