© 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. 11-GEMMASCOPE-RES-16K
    11. 6457
    Prev
    Next
    INDEX
    Explanations

    indications of significant concepts or upcoming topics in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.74
     HttpNotFound
    -0.51
     Navig
    -0.50
     infide
    -0.47
    Navig
    -0.47
     utafiti
    -0.47
    ListItemIcon
    -0.46
     TextInputType
    -0.46
     bronz
    -0.45
     Offisielt
    -0.44
    POSITIVE LOGITS
    ніципалі
    0.64
    tagHelperRunner
    0.62
     '\\;'
    0.62
    runApp
    0.61
    WindowConstants
    0.60
     createState
    0.59
    ValueStyle
    0.56
     "..\..\
    0.53
    ViewChild
    0.53
    RequiresApi
    0.53
    Activations Density 0.471%

    No Known Activations