© 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. 14-GEMMASCOPE-RES-16K
    6. 10432
    Prev
    Next
    INDEX
    Explanations

    technical terms related to optimization and measurement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.51
    CDCl
    -0.49
    :✨
    -0.47
     оригіналу
    -0.46
     unopened
    -0.46
    یک
    -0.44
     contrário
    -0.41
    floor
    -0.40
     Consejo
    -0.40
    随着
    -0.39
    POSITIVE LOGITS
    __":
    
    0.85
    __':
    
    0.83
    InSection
    0.82
    __":
    0.73
    RectangleBorder
    0.72
    ngdoc
    0.67
    ValueStyle
    0.66
    HtmlAttribute
    0.66
    
    
    0.63
    новниш
    0.63
    Activations Density 0.829%

    No Known Activations