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. 3152
    Prev
    Next
    INDEX
    Explanations

    references to mental health or psychosocial topics related to women

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

    Comparative adjectives and adverbs

    np_acts-logits-general · gemini-2.0-flash

    comparisons with more or less

    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
    zości
    -0.53
    consulté
    -0.51
    InjectAttribute
    -0.47
     bVar
    -0.46
    spyOn
    -0.45
    ześnie
    -0.45
    UnusedPrivate
    -0.44
    ResumeLayout
    -0.44
    BoxShadow
    -0.43
    Tja
    -0.42
    POSITIVE LOGITS
     stronger
    2.41
     easier
    2.34
     better
    2.31
     quicker
    2.24
     faster
    2.22
     clearer
    2.22
     harder
    2.19
     richer
    2.18
     more
    2.17
     sharper
    2.17
    Activations Density 4.095%

    No Known Activations