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. 16-GEMMASCOPE-RES-16K
    6. 13003
    Prev
    Next
    INDEX
    Explanations

    structured frameworks for collaboration and organization within educational and community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noinspection
    -0.65
    хьтан
    -0.63
    hoeddwyd
    -0.59
    CopyWith
    -0.58
    Спољашње
    -0.57
    Referências
    -0.55
    abestanden
    -0.55
    ScrollPane
    -0.54
     cref
    -0.54
    تفصیلات
    -0.53
    POSITIVE LOGITS
     dedicated
    0.68
    principalTable
    0.62
     consac
    0.58
     enabling
    0.57
     consisting
    0.55
     devoted
    0.55
     designed
    0.55
     symbo
    0.54
     named
    0.52
     composed
    0.51
    Activations Density 0.780%

    No Known Activations