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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 10867
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "as" in various contexts

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

    "As" followed by a preposition or adverb

    np_acts-logits-general · gemini-2.0-flash

    as X pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.72
     itſelf
    -0.72
     Jefus
    -0.70
     ſever
    -0.68
     juſt
    -0.67
    こと
    -0.64
     ſeveral
    -0.62
    StoryboardSegue
    -0.62
     Anſ
    -0.60
     raiſ
    -0.60
    POSITIVE LOGITS
     part
    1.09
     follows
    1.07
     well
    1.06
     far
    0.95
     opposed
    0.93
    follows
    0.92
     soon
    0.91
    pires
    0.91
     a
    0.90
    part
    0.80
    Activations Density 0.344%

    No Known Activations