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. 14563
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and its various forms or contexts within sentences

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

    "in" followed by possessive pronouns, articles, or adjectives

    np_acts-logits-general · gemini-2.0-flash

    referring to previous statements

    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
     للمعارف
    -0.84
    IUrlHelper
    -0.82
    ArrowToggle
    -0.80
    TagMode
    -0.75
    saraba
    -0.74
     مرئيه
    -0.70
    anything
    -0.68
    WithIOException
    -0.67
     متعلقه
    -0.65
    
    -0.64
    POSITIVE LOGITS
     recent
    0.62
     earlier
    0.59
     passing
    0.55
     blog
    0.54
     separate
    0.53
     détour
    0.53
     previous
    0.53
     blogs
    0.52
    itsch
    0.52
    сколь
    0.51
    Activations Density 0.403%

    No Known Activations