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. 2015
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or references to dates

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

    "0" immediately followed by "1"

    np_acts-logits-general · gemini-2.0-flash

    dates and deadlines

    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
    tagHelperRunner
    -0.81
     snippetHide
    -0.70
     كومونز
    -0.70
     بيها
    -0.70
    HomeAsUp
    -0.69
    uxxxx
    -0.69
    !*\
    -0.69
     bezeichneter
    -0.68
    \}\\
    -0.66
     ویکی‌پدیا
    -0.65
    POSITIVE LOGITS
    un
    0.48
    igil
    0.48
    を重ね
    0.47
      
    0.46
    oque
    0.46
     "
    0.44
     فصل
    0.42
    гун
    0.42
    boldsymbol
    0.42
    arası
    0.42
    Activations Density 0.394%

    No Known Activations