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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8584
    Prev
    Next
    INDEX
    Explanations

    references to materials and textures in descriptions

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

    Describes texture and tactile properties

    np_acts-logits-general · gemini-2.0-flash

    tactile qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    openzeppelin
    -0.49
    viewDid
    -0.43
     Kaffee
    -0.43
    redo
    -0.43
     qualified
    -0.42
     Alliance
    -0.42
     pertinentes
    -0.42
     pertinente
    -0.42
    νομα
    -0.41
     příslu
    -0.41
    POSITIVE LOGITS
     softness
    1.33
     texture
    1.15
     smoothness
    1.10
     smooth
    1.10
     soft
    1.09
     softer
    1.02
     silky
    1.01
     Texture
    0.99
    smooth
    0.98
     slippery
    0.98
    Activations Density 0.271%

    No Known Activations