© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14041
    Prev
    Next
    INDEX
    Explanations

    elements related to tracking, locating, and searching for people or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    TagMode
    -0.43
     Commen
    -0.43
    EDEFAULT
    -0.42
    XmlAccessType
    -0.40
    ختی
    -0.39
     lho
    -0.39
    faits
    -0.38
     Fron
    -0.38
    merit
    -0.38
    WebMethod
    -0.37
    POSITIVE LOGITS
     locating
    0.78
     찾
    0.75
     locate
    0.70
     whereabouts
    0.68
    찾
    0.67
     search
    0.66
    locate
    0.62
     hunt
    0.61
     finding
    0.61
     searches
    0.61
    Activations Density 0.454%

    No Known Activations