© 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. 14919
    Prev
    Next
    INDEX
    Explanations

    verbs associated with understanding, sharing knowledge, and interactions with others

    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
    AnchorTagHelper
    -0.51
     AssemblyCompany
    -0.48
    marginVertical
    -0.48
    eningrad
    -0.47
    そんな
    -0.44
     useDispatch
    -0.43
    ")]
    -0.43
    UNRELATED
    -0.43
    ytt
    -0.43
    зг
    -0.42
    POSITIVE LOGITS
     alongside
    0.63
     personally
    0.61
     yourself
    0.61
     themselves
    0.61
     oneself
    0.60
     absolument
    0.60
    HtmlAttribute
    0.59
     yourselves
    0.59
     ourselves
    0.58
    /*
    0.57
    Activations Density 0.247%

    No Known Activations