© 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. 15-GEMMASCOPE-RES-16K
    11. 4827
    Prev
    Next
    INDEX
    Explanations

    header elements in a structured document, particularly those with 'h' and 'uint' data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -1.07
    ArrowToggle
    -0.84
    MessageTagHelper
    -0.72
    Климат
    -0.72
    ItemBackground
    -0.71
    ่านั้น
    -0.70
     protoimpl
    -0.69
     africano
    -0.69
     Egli
    -0.67
     moonlight
    -0.66
    POSITIVE LOGITS
    ########.
    0.74
    ientí
    0.66
     coff
    0.61
    styleUrls
    0.60
    arrol
    0.58
     Hamb
    0.57
    ionView
    0.57
     Utf
    0.57
     ipv
    0.57
     BEHAV
    0.56
    Activations Density 0.135%

    No Known Activations