© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14012
    Prev
    Next
    INDEX
    Explanations

    information related to materials and their properties, particularly metals and composites used in manufacturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metal
    -0.73
     Metal
    -0.71
    Metal
    -0.71
    metal
    -0.68
    METAL
    -0.67
     METAL
    -0.65
     métal
    -0.65
     металли
    -0.62
     metallic
    -0.61
    金属
    -0.61
    POSITIVE LOGITS
     marten
    0.59
     temper
    0.57
     hardness
    0.52
     aust
    0.52
     tempered
    0.50
     precipitation
    0.49
    tempered
    0.46
     Carpenter
    0.46
     зака
    0.46
     Temp
    0.46
    Activations Density 0.442%

    No Known Activations