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. 16-GEMMASCOPE-RES-16K
    6. 6394
    Prev
    Next
    INDEX
    Explanations

    references to scientific theories and findings related to virulence and pathogen interactions

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

    preceding relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    introduces relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.78
    zzleHttp
    -0.64
     HttpNotFound
    -0.59
    цездатний
    -0.58
    VIAF
    -0.58
    jspx
    -0.56
    awtextra
    -0.54
    EDEFAULT
    -0.53
    HasAnnotation
    -0.53
    tanleria
    -0.52
    POSITIVE LOGITS
     which
    1.03
     where
    0.99
    which
    0.88
     whose
    0.86
     wherein
    0.83
     whereby
    0.80
    where
    0.80
     who
    0.79
     जहां
    0.79
    whose
    0.73
    Activations Density 0.440%

    No Known Activations