Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122386
    Prev
    Next
    INDEX
    Explanations

    terms related to gaze and visual attention strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    BufferException
    -0.65
    AddTagHelper
    -0.60
    enderror
    -0.60
     AssemblyVersion
    -0.58
    SpringBootTest
    -0.58
     transfieras
    -0.57
     surla
    -0.57
     combineReducers
    -0.55
    حياته
    -0.53
    POSITIVE LOGITS
     gaze
    0.41
     eye
    0.41
     attention
    0.39
    attention
    0.37
     glance
    0.36
    focusable
    0.35
     caméra
    0.35
    eye
    0.34
    AutoModerator
    0.34
     depth
    0.34
    Activations Density 0.022%

    No Known Activations