© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14236
    Prev
    Next
    INDEX
    Explanations

    structural and material characteristics of buildings, particularly roofs and flooring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.54
    AndEndTag
    -0.49
    StructEnd
    -0.41
    pædia
    -0.41
    Parcelize
    -0.40
    嘧
    -0.40
    zijde
    -0.40
     nahilalakip
    -0.37
    ælp
    -0.37
    ographia
    -0.36
    POSITIVE LOGITS
     floor
    1.70
     flooring
    1.63
     Floor
    1.51
     floors
    1.50
     FLOOR
    1.48
    Floor
    1.45
    floor
    1.43
     carpet
    1.40
     Flooring
    1.33
     lantai
    1.28
    Activations Density 0.206%

    No Known Activations