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. 13772
    Prev
    Next
    INDEX
    Explanations

    verbs and their various forms indicating movement or action

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    went on or to

    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
     myſelf
    -0.62
     deſt
    -0.59
     ſtate
    -0.58
     TextInputType
    -0.58
     stiefel
    -0.57
    GEBURTSDATUM
    -0.57
     ſy
    -0.55
     Jefus
    -0.55
     rodríguez
    -0.55
     sonne
    -0.55
    POSITIVE LOGITS
    ">//
    0.60
    mainAxisSize
    0.53
    lapsingToolbar
    0.52
    Välislingid
    0.49
    queryInterface
    0.49
     went
    0.49
     ComVisible
    0.48
     full
    0.48
    ])):
    0.48
     hard
    0.47
    Activations Density 0.066%

    No Known Activations