Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4979
    Prev
    Next
    INDEX
    Explanations

    mathematical and computational concepts

    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
     فريبيس
    -0.65
    +#+#
    -0.63
     المعيارى
    -0.55
    Rhestr
    -0.52
     informée
    -0.50
    aarrggbb
    -0.50
    مراجع
    -0.50
    CppMethod
    -0.50
     }{@
    -0.49
    XmlAccessType
    -0.48
    POSITIVE LOGITS
    帖最后由
    0.74
    ']")
    0.70
    oredCriteria
    0.67
     PyLong
    0.66
     neceff
    0.66
    contentLoaded
    0.65
    TagMode
    0.63
     Chriftian
    0.60
    AddTagHelper
    0.59
     ſeveral
    0.58
    Activations Density 0.798%

    No Known Activations