© 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. 22-GEMMASCOPE-RES-16K
    11. 13213
    Prev
    Next
    INDEX
    Explanations

    elements related to web development frameworks and their functionalities

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

    visibility (hidden, visible)

    np_acts-logits-general · gemini-2.0-flash

    visual states like visible, hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.60
    makeConstraints
    -0.58
    Chú
    -0.56
    DataAnnotations
    -0.54
    ագրություններ
    -0.53
    Ծանոթ
    -0.51
    AxisAlignment
    -0.51
     تضيفلها
    -0.51
    endforeach
    -0.48
    NameInMap
    -0.48
    POSITIVE LOGITS
     visibility
    1.94
     visible
    1.78
    visibility
    1.74
     Visibility
    1.73
    Visibility
    1.67
    visible
    1.65
     hide
    1.64
    Visible
    1.62
     hidden
    1.60
     invisible
    1.57
    Activations Density 0.239%

    No Known Activations