© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13703
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing and injection molding processes

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

    Molding and manufacturing processes

    np_acts-logits-general · gemini-2.0-flash

    mold and casting components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الاطلاع
    -0.65
     kasarigan
    -0.62
     papyrus
    -0.51
     récon
    -0.51
    ंदीखरीदारी
    -0.50
     للمعارف
    -0.50
    isement
    -0.50
     ngang
    -0.49
     scalars
    -0.49
    engeti
    -0.48
    POSITIVE LOGITS
     mold
    1.11
     molds
    1.10
     mould
    1.03
     moulds
    0.99
     tooling
    0.99
     casting
    0.98
     molding
    0.96
     die
    0.94
     moldes
    0.92
     Mold
    0.92
    Activations Density 0.559%

    No Known Activations