© 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. 1-GEMMASCOPE-RES-16K
    11. 14724
    Prev
    Next
    INDEX
    Explanations

    references to the abbreviation "FL" and its associated context, particularly relating to Florida

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceral
    -0.68
     Edelman
    -0.64
     Schaefer
    -0.64
    CORBA
    -0.60
     Kep
    -0.60
     Cowell
    -0.58
     joyeux
    -0.58
     quæ
    -0.58
    yorsunuz
    -0.57
     puits
    -0.56
    POSITIVE LOGITS
     FL
    2.75
     flu
    2.66
     Flu
    2.65
     fl
    2.57
    Flu
    2.55
    flu
    2.53
    FL
    2.51
     Fl
    2.51
    Fl
    2.41
    fl
    2.35
    Activations Density 0.068%

    No Known Activations