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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 8677
    Prev
    Next
    INDEX
    Explanations

    references to the journal "Nature."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.90
    ؤلاء
    -0.77
     illum
    -0.76
    ✨:
    -0.73
     Schuyler
    -0.73
     SqlCommand
    -0.72
     RIPRODUZIONE
    -0.71
    تفصیلات
    -0.71
     fhew
    -0.70
     noblesse
    -0.70
    POSITIVE LOGITS
     NATURE
    1.34
     Nature
    1.29
     nature
    1.27
    NATURE
    1.15
    Nature
    1.08
     Natur
    0.99
     natures
    0.97
    nature
    0.96
    Natur
    0.94
     natureza
    0.93
    Activations Density 0.046%

    No Known Activations