© 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. 3-GEMMASCOPE-RES-16K
    11. 7115
    Prev
    Next
    INDEX
    Explanations

    instances of the term "off" as well as context related to breaks or time away

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.71
    webElementXpaths
    -0.56
     propOrder
    -0.53
     salita
    -0.52
    DispatchToProps
    -0.51
    AfterClass
    -0.51
    bnf
    -0.50
    ioutil
    -0.50
     RequestMethod
    -0.49
    XmlAccessorType
    -0.47
    POSITIVE LOGITS
    ViewImports
    0.75
    __*/
    0.67
    Становништво
    0.58
     arşivlendi
    0.56
     utafitiHapana
    0.56
    oas
    0.56
    Diwedd
    0.54
    protoimpl
    0.54
    oxone
    0.54
     chi̍t
    0.54
    Activations Density 0.520%

    No Known Activations