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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53094
    Prev
    Next
    INDEX
    Explanations

    references to wooden materials and furniture

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

    wooden items and constructions

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    SizeF
    -0.74
    IUrlHelper
    -0.74
     myſelf
    -0.69
    tvguidetime
    -0.64
     odkazy
    -0.64
    Obrázky
    -0.63
     Reſ
    -0.62
    łaszcza
    -0.60
    upol
    -0.60
     Thời
    -0.59
    POSITIVE LOGITS
     wood
    1.34
     timber
    1.24
     wooden
    1.24
     Wooden
    1.23
     Wood
    1.23
    Wooden
    1.16
     Holz
    1.15
     WOOD
    1.13
    Wood
    1.10
    wooden
    1.09
    Activations Density 0.088%

    No Known Activations