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. 25-GEMMASCOPE-RES-16K
    6. 5710
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to material properties and behaviors under stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
    geslacht
    -0.55
    enumi
    -0.55
    extField
    -0.52
    Obrázky
    -0.51
     resourceCulture
    -0.49
    RegistryLite
    -0.49
    dflare
    -0.49
     unplayable
    -0.48
    ㅤ
    -0.48
    POSITIVE LOGITS
     inversely
    0.86
     dependence
    0.83
     proportional
    0.78
     linearly
    0.77
     dependency
    0.74
    propto
    0.73
     increasing
    0.73
     dependent
    0.73
     decreasing
    0.72
     dependents
    0.72
    Activations Density 1.753%

    No Known Activations