© 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. 4-GEMMASCOPE-RES-16K
    11. 11400
    Prev
    Next
    INDEX
    Explanations

    expressions of positivity and quality in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loyalty
    -0.56
     Yee
    -0.52
    حوالہ
    -0.52
    SerializedSize
    -0.51
     BufferedImage
    -0.51
    сев
    -0.51
     jPanel
    -0.50
    Loyalty
    -0.50
    (:,:,
    -0.50
     ripening
    -0.50
    POSITIVE LOGITS
    存于互联网档案馆
    0.84
     disambiguazione
    0.76
     okay
    0.76
     alright
    0.70
    UnsafeEnabled
    0.69
     Wikimedijinoj
    0.68
    RSpec
    0.68
     enough
    0.67
     bagus
    0.65
    sizeCache
    0.62
    Activations Density 0.215%

    No Known Activations