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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14670
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and file handling in various coding contexts

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

    File paths or module names

    np_acts-logits-general · gemini-2.0-flash

    file paths

    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
    SharedDtor
    -0.88
    AsUp
    -0.87
     tartalomajánló
    -0.68
    CppCodeGen
    -0.68
    TProtocol
    -0.66
    .*")]
    -0.66
     <>",
    -0.66
    (!__
    -0.65
     ویکی‌پدیای
    -0.63
    ValueStyle
    -0.63
    POSITIVE LOGITS
    ילו
    0.59
    Przypisy
    0.55
     يتيمه
    0.52
     BioLib
    0.50
    strcat
    0.50
     schre
    0.47
    ച്
    0.47
     beda
    0.47
    ghijklmnop
    0.47
    photobucket
    0.46
    Activations Density 0.316%

    No Known Activations