© 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. 18-GEMMASCOPE-RES-16K
    11. 1668
    Prev
    Next
    INDEX
    Explanations

    references to the concept of being "blind" in various contexts

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

    "blind"

    np_acts-logits-general · gemini-2.0-flash

    blind and associated words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.87
    HasAnnotation
    -0.78
    FormTagHelper
    -0.71
    AndEndTag
    -0.70
    tagHelperRunner
    -0.70
    TagMode
    -0.67
    WebElementEntity
    -0.66
     jPanel
    -0.61
    الإنجليزية
    -0.61
     Superhost
    -0.61
    POSITIVE LOGITS
    Blind
    0.72
    folded
    0.70
     Blind
    0.63
    folds
    0.63
     FRE
    0.61
     blind
    0.57
    FRE
    0.57
    EnableWeb
    0.57
    blind
    0.55
     Catawiki
    0.55
    Activations Density 0.182%

    No Known Activations