© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 4136
    Prev
    Next
    INDEX
    Explanations

    technical terms related to graphics rendering and shaders

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

    signal processing or image manipulation

    np_acts-logits-general · gemini-2.0-flash

    effects and instrumental processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.60
    didSet
    -0.54
    enumi
    -0.53
    figer
    -0.52
    futbolista
    -0.52
    belea
    -0.51
     ovi
    -0.51
    ็ง
    -0.50
     Sinter
    -0.50
     Bind
    -0.49
    POSITIVE LOGITS
     effects
    0.99
     effect
    0.98
     Effects
    0.94
    effect
    0.88
     Effect
    0.87
    Effects
    0.87
     processing
    0.83
    effects
    0.82
    Effect
    0.81
     efecto
    0.79
    Activations Density 0.419%

    No Known Activations