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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35378
    Prev
    Next
    INDEX
    Explanations

    programming concepts and issues related to web development, particularly in relation to rendering and processing HTML elements

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

    animation disappears and never restarts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     stip
    -0.47
     <<<<<<<<<<<<<<
    -0.47
     convention
    -0.45
     informée
    -0.42
    Convention
    -0.42
     verru
    -0.42
    Stern
    -0.42
    Miles
    -0.40
     kinase
    -0.40
     Convention
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.52
    SharedDtor
    0.44
     seolah
    0.44
     weirdly
    0.44
    nvarchar
    0.43
    expandindo
    0.42
     unnecessarily
    0.42
    audiovisuel
    0.40
     blindly
    0.40
     abruptly
    0.39
    Activations Density 0.178%

    No Known Activations