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. 0-GEMMASCOPE-RES-16K
    6. 3383
    Prev
    Next
    INDEX
    Explanations

    references to specific historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evos
    -0.60
     Beatty
    -0.57
    erenc
    -0.56
    tagHelper
    -0.51
    حياته
    -0.51
     renda
    -0.50
    省市镇
    -0.49
    +#+#
    -0.48
    gion
    -0.48
     candidats
    -0.48
    POSITIVE LOGITS
     CGSize
    0.78
     AssemblyTitle
    0.75
    vent
    0.74
    存于互联网档案馆
    0.71
    HomeAsUpEnabled
    0.70
     Efq
    0.70
     Autorizaciones
    0.68
     deten
    0.68
    SharedDtor
    0.67
     onPostExecute
    0.67
    Activations Density 2.801%

    No Known Activations