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. 22-GEMMASCOPE-RES-16K
    6. 14082
    Prev
    Next
    INDEX
    Explanations

    structural components and relationships within programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.69
     Efq
    -0.61
     normaux
    -0.60
     internationaux
    -0.59
     fhould
    -0.59
     MainAxisSize
    -0.59
    Koordinaten
    -0.58
     跳转至
    -0.57
     Abgerufen
    -0.57
     Grecs
    -0.57
    POSITIVE LOGITS
     student
    0.79
     employee
    0.79
     users
    0.76
     product
    0.72
     book
    0.70
     Users
    0.69
     students
    0.67
     movie
    0.67
     Student
    0.67
     books
    0.67
    Activations Density 0.391%

    No Known Activations