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. 12-GEMMASCOPE-RES-16K
    6. 4328
    Prev
    Next
    INDEX
    Explanations

    phrases indicating levels or degrees of various attributes or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izop
    -0.81
     Şi
    -0.73
     Selby
    -0.69
     giovan
    -0.68
     garant
    -0.68
     muzik
    -0.67
     Niz
    -0.67
     ['./
    -0.66
    zyb
    -0.66
    ,:]
    -0.66
    POSITIVE LOGITS
     degrees
    1.49
     Degrees
    1.47
     degree
    1.36
     Degree
    1.32
    Degrees
    1.31
     DEGREE
    1.28
    Degree
    1.28
    degrees
    1.25
    degree
    1.22
    GREES
    1.16
    Activations Density 0.095%

    No Known Activations