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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 616
    Prev
    Next
    INDEX
    Explanations

    elements related to graphics programming or shader definitions

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

    shaders and graphics programming

    np_acts-logits-general · gemini-2.0-flash

    GLSL uniform variables

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     CURIAM
    -0.53
    存于互联网档案馆
    -0.53
    NewReader
    -0.51
    Aiheesta
    -0.50
    сылкі
    -0.48
    PageRoute
    -0.47
    Superview
    -0.46
    sleep
    -0.46
     légale
    -0.46
    buttonShape
    -0.45
    POSITIVE LOGITS
    ::::::::
    0.63
     /\.(
    0.61
     Phong
    0.61
     ARB
    0.60
     albedo
    0.60
     WebGL
    0.60
    ARB
    0.60
     OpenGL
    0.60
     Mesopo
    0.59
    Программа
    0.59
    Activations Density 0.359%

    No Known Activations