© 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. 23-GEMMASCOPE-RES-16K
    11. 11889
    Prev
    Next
    INDEX
    Explanations

    references to a specific place or location, particularly those related to "Bel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.78
     himo
    -0.71
    hysema
    -0.65
    DockStyle
    -0.61
    CodedInputStream
    -0.59
     geweest
    -0.58
    tagHelperRunner
    -0.57
    bootstrapcdn
    -0.56
    SourceChecksum
    -0.55
    enumi
    -0.54
    POSITIVE LOGITS
    IsContent
    0.65
     Bel
    0.64
     BEL
    0.63
    Bel
    0.55
     bel
    0.54
    staff
    0.48
    BeforeClass
    0.47
     Helicopter
    0.47
    >`;
    0.47
     Marra
    0.47
    Activations Density 0.140%

    No Known Activations