© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 14943
    Prev
    Next
    INDEX
    Explanations

    references to data structures or concepts that indicate emptiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.83
    ^(@)
    -0.79
     houſe
    -0.76
     ſame
    -0.72
    Démographie
    -0.71
     Jefus
    -0.71
    ษา
    -0.69
    AnchorTagHelper
    -0.68
    Datuak
    -0.68
    AndroidJUnit
    -0.68
    POSITIVE LOGITS
    IsRequired
    1.09
     <=",
    0.95
    PathVariable
    0.86
    청
    0.82
    itm
    0.71
     متعلقه
    0.68
    dcterms
    0.63
    DockStyle
    0.56
    spro
    0.54
    lugin
    0.54
    Activations Density 0.000%

    No Known Activations