Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3832
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to thread exceptions and management

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

    "thread" (computing/sewing)

    np_acts-logits-general · gemini-2.0-flash

    thread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.05
     myſelf
    -0.96
    AndEndTag
    -0.93
     Audiodateien
    -0.93
    Rujuakan
    -0.90
     pinulongan
    -0.90
    вгений
    -0.89
     poffible
    -0.89
     تضيفلها
    -0.88
    JspWriter
    -0.84
    POSITIVE LOGITS
     THREAD
    1.37
     thread
    1.29
     threads
    1.28
     Thread
    1.23
    Threads
    1.20
    Thread
    1.18
    thread
    1.16
    threads
    1.14
     Threads
    1.13
    THREAD
    1.12
    Activations Density 0.130%

    No Known Activations