© 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. 21-GEMMASCOPE-RES-16K
    11. 14914
    Prev
    Next
    INDEX
    Explanations

    text that discusses cookie policies and user consent regarding cookie usage on websites

    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
    -------------</
    -0.65
    出版年
    -0.58
    HomeAsUpEnabled
    -0.54
    MetaObject
    -0.53
    pegno
    -0.53
    tele
    -0.53
    dial
    -0.48
    Jeografia
    -0.47
    athread
    -0.46
    pushFollow
    -0.46
    POSITIVE LOGITS
     cookies
    1.61
     cookie
    1.52
     Cookies
    1.46
     Cookie
    1.40
    Cookies
    1.33
    cookies
    1.29
    Cookie
    1.27
    cookie
    1.27
     COOKIE
    1.26
     COOKIES
    1.19
    Activations Density 0.131%

    No Known Activations