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. 2280
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific methods and techniques used in research

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

    "[something] is [adverb]" sentences

    np_acts-logits-general · gemini-2.0-flash

    is followed by state or condition

    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
     yours
    -0.59
     theirs
    -0.59
    dorfer
    -0.57
     gonna
    -0.54
     doing
    -0.53
    arran
    -0.51
    aget
    -0.51
     ACTUALLY
    -0.51
    dbl
    -0.50
    कार
    -0.50
    POSITIVE LOGITS
     increasingly
    0.88
    setVerticalGroup
    0.88
     notoriously
    0.86
    principalColumn
    0.82
    EndGlobalSection
    0.79
     widely
    0.74
     frequently
    0.72
    increasing
    0.72
     often
    0.70
     currently
    0.68
    Activations Density 0.748%

    No Known Activations