© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11042
    Prev
    Next
    INDEX
    Explanations

    elements related to data attributes and their properties in a structured format, such as whether they are nullable or have default values

    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
    jsonwebtoken
    -0.72
     насељу
    -0.70
    richTextPanel
    -0.70
    OPSIS
    -0.66
     بتاريخ
    -0.66
     unknownFields
    -0.64
    ArrowToggle
    -0.62
    rija
    -0.62
     الحره
    -0.61
     otomatig
    -0.61
    POSITIVE LOGITS
    AutoScaleMode
    0.70
    AnchorStyles
    0.68
     Exacts
    0.66
     المعرف
    0.61
    ArgsConstructor
    0.61
     CreateTagHelper
    0.61
     säll
    0.57
     Diarsipkan
    0.56
     PhpStorm
    0.56
    UseVisualStyle
    0.54
    Activations Density 0.074%

    No Known Activations