© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8248
    Prev
    Next
    INDEX
    Explanations

    technical terms and coding constructs related to software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encodeWith
    -0.62
    IndentedString
    -0.54
    InitVars
    -0.47
    Халык
    -0.46
    SetString
    -0.46
     prison
    -0.45
    Portály
    -0.45
     चीज़ों
    -0.45
    Predecesor
    -0.44
    tvguidetime
    -0.44
    POSITIVE LOGITS
    :+:
    0.64
     Ore
    0.61
    headers
    0.59
    kuuta
    0.58
    orianCalendar
    0.57
    tagHelperRunner
    0.56
     vacancies
    0.55
     ORE
    0.54
     rowspan
    0.54
     vacancy
    0.53
    Activations Density 2.861%

    No Known Activations