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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 271
    Prev
    Next
    INDEX
    Explanations

    terms related to botanical classifications and plant characteristics

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

    scientific and botanical taxonomic terminology, particularly related to herbaria, plant species, and botanical classification.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    ########.
    -0.52
     OFDb
    -0.49
     bezeichneter
    -0.47
    XmlEnum
    -0.43
     Hift
    -0.41
     purpoſe
    -0.41
    
    -0.41
    IsContent
    -0.41
    IntoConstraints
    -0.40
     itſelf
    -0.40
    POSITIVE LOGITS
    ftagPool
    0.44
    setof
    0.43
     seedlings
    0.42
    TargetException
    0.42
     seedling
    0.41
    Shoot
    0.40
    来人
    0.40
     shoots
    0.39
     shoot
    0.39
    ☚
    0.38
    Activations Density 0.115%

    No Known Activations