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. 13-GEMMASCOPE-RES-16K
    6. 542
    Prev
    Next
    INDEX
    Explanations

    discussions about recognition and admiration for individuals or groups playing significant, often heroic roles in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.87
     насељу
    -0.81
    setVerticalGroup
    -0.80
    TagMode
    -0.77
    expandindo
    -0.74
    Geplaatst
    -0.73
     ExecuteAsync
    -0.67
    ніципалі
    -0.65
    +#+#
    -0.62
    CppMethod
    -0.62
    POSITIVE LOGITS
     ddelweddau
    0.52
     palsu
    0.46
    hluk
    0.45
     Gutes
    0.44
     hâte
    0.43
    choix
    0.42
    uticos
    0.42
     seleccione
    0.41
    sự
    0.40
    tainty
    0.40
    Activations Density 0.417%

    No Known Activations