© 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. 12-GEMMASCOPE-RES-16K
    6. 16170
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing and digital image processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or scientific terms and acronyms (domain-specific jargon and capitalized multiword technical phrases).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.77
    BASEPATH
    -0.73
    routeProvider
    -0.69
    XtraEditors
    -0.68
    AnchorTagHelper
    -0.66
     Мексичка
    -0.63
    IBOutlet
    -0.61
    DoubleQuotes
    -0.61
     disambiguazione
    -0.60
    BindingResult
    -0.60
    POSITIVE LOGITS
    kloped
    0.65
    IsContent
    0.63
    DNA
    0.54
    новниш
    0.52
    MADRID
    0.51
     okuyayım
    0.48
     Enabled
    0.48
    ℠
    0.48
    Instead
    0.47
    instead
    0.46
    Activations Density 2.580%

    No Known Activations