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. 1402
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental or institutional regulations and financial aspects

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

    Comes before "which" or similar relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    which or whose

    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
     accordingly
    -0.82
     alike
    -0.72
    的同时
    -0.69
     while
    -0.68
    HasAnnotation
    -0.63
     whilst
    -0.57
     además
    -0.57
     until
    -0.57
     instead
    -0.56
    并
    -0.55
    POSITIVE LOGITS
     which
    1.57
    which
    1.39
     WHICH
    1.08
     whose
    1.02
     Which
    0.99
    whose
    0.99
     who
    0.97
    Which
    0.94
    hich
    0.90
    ซึ่ง
    0.86
    Activations Density 0.671%

    No Known Activations