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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 4580
    Prev
    Next
    INDEX
    Explanations

    technical terms related to materials and their properties, especially metals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Woodbury
    -0.56
     narcotic
    -0.53
     cacher
    -0.52
     velas
    -0.52
    posób
    -0.52
     Luci
    -0.51
     narcotics
    -0.51
     virtuel
    -0.51
    ŚĆ
    -0.51
    Matrix
    -0.50
    POSITIVE LOGITS
     steel
    1.19
     Steel
    0.99
    steel
    0.94
    Steel
    0.91
     metal
    0.90
     iron
    0.90
     sheet
    0.88
     alloy
    0.88
     welded
    0.87
     stainless
    0.87
    Activations Density 0.235%

    No Known Activations