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. 21-GEMMASCOPE-RES-16K
    6. 6657
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming structures, particularly those involving data retrieval or configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.51
    (
    -0.50
    AndEndTag
    -0.48
    сия
    -0.47
    <eos>
    -0.44
    H
    -0.42
    .
    -0.41
     Malhotra
    -0.40
    EntityFramework
    -0.40
     zapatos
    -0.40
    POSITIVE LOGITS
    TagMode
    0.81
    StoryboardSegue
    0.79
     مشين
    0.78
    الدراسه
    0.71
     MotionEvent
    0.71
     وتسجيلات
    0.70
     iſt
    0.68
    adeloupe
    0.66
    esterday
    0.65
    ſelves
    0.65
    Activations Density 0.015%

    No Known Activations