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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 11241
    Prev
    Next
    INDEX
    Explanations

    terms related to memory technology and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     v
    -0.42
    sip
    -0.41
    ľa
    -0.40
    族館
    -0.40
     World
    -0.40
    iro
    -0.40
    피
    -0.40
    ingular
    -0.39
    klady
    -0.39
     proposés
    -0.39
    POSITIVE LOGITS
     AssemblyCompany
    0.75
    SharedDtor
    0.73
     متعلقه
    0.71
     resourceCulture
    0.68
    tagHelperRunner
    0.64
     gyhoeddwyd
    0.63
     виправивши
    0.63
    WebServlet
    0.62
    Chham
    0.61
    SpringRunner
    0.61
    Activations Density 0.986%

    No Known Activations