© 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. 21-GEMMASCOPE-RES-16K
    6. 6259
    Prev
    Next
    INDEX
    Explanations

    specific characteristics or attributes pertaining to subjects discussed in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infatti
    -0.75
     ویکی‌پدی
    -0.74
     NSCoder
    -0.73
    jenige
    -0.72
    InjectAttribute
    -0.69
    Hentet
    -0.65
    +#+
    -0.64
    AnchorTagHelper
    -0.62
    AndEndTag
    -0.60
     olyan
    -0.59
    POSITIVE LOGITS
     leaſt
    0.87
     hopefully
    0.81
     myſelf
    0.80
     purpoſe
    0.77
     uſed
    0.76
     otherwise
    0.75
     themſelves
    0.72
     ſtand
    0.71
     cauſe
    0.70
     himſelf
    0.70
    Activations Density 0.480%

    No Known Activations