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. 25-GEMMASCOPE-RES-16K
    6. 10206
    Prev
    Next
    INDEX
    Explanations

    elements related to academic qualifications and achievements, particularly PhD theses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.57
     المعيارى
    -0.56
    Пря
    -0.55
    NameInMap
    -0.53
    elry
    -0.52
    ství
    -0.52
     linkovi
    -0.52
    IANGLES
    -0.50
    oneph
    -0.50
    igrette
    -0.48
    POSITIVE LOGITS
     thesis
    1.50
     Thesis
    1.37
    Thesis
    1.29
     dissertation
    1.29
     Dissertation
    1.22
    thesis
    1.19
    Dissertation
    1.13
     THESIS
    1.11
     thèse
    0.99
     PhD
    0.99
    Activations Density 0.315%

    No Known Activations