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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35629
    Prev
    Next
    INDEX
    Explanations

    references to shadow mapping and rendering techniques

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

    OpenGL, Scene Graph, Albedo

    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
    cemment
    -0.43
    rawDesc
    -0.31
    opardy
    -0.29
    Semaphore
    -0.28
    gauge
    -0.28
    com
    -0.27
     voltaje
    -0.27
     graden
    -0.26
    Typing
    -0.26
    Palmar
    -0.26
    POSITIVE LOGITS
    PostInfinity
    0.79
    Xna
    0.74
    PreInfinity
    0.70
    tangentMode
    0.69
    aarrggbb
    0.68
     AssemblyProduct
    0.68
     esternos
    0.66
    Aholisi
    0.65
     BoxFit
    0.64
    /*
    0.63
    Activations Density 0.142%

    No Known Activations