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. 14072
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements

    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
     المعيارى
    -1.30
    mybatisplus
    -1.23
    Datuak
    -1.22
     NSCoder
    -1.21
     kasarigan
    -1.19
    ########.
    -1.19
     مشين
    -1.18
     متعلقه
    -1.17
    uxxxx
    -1.17
    rungsseite
    -1.16
    POSITIVE LOGITS
     (
    0.81
     
    0.78
     the
    0.71
     new
    0.67
    ↵
    0.65
    if
    0.64
     a
    0.64
    1
    0.64
    is
    0.59
     "
    0.59
    Activations Density 0.689%

    No Known Activations