Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5978
    Prev
    Next
    INDEX
    Explanations

    references to "South" in geographical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -1.08
    modelBuilder
    -0.83
    GEBURTSDATUM
    -0.83
     Marlin
    -0.83
     Roskov
    -0.82
    PMailer
    -0.82
     Winaray
    -0.80
    inquirer
    -0.79
     PKK
    -0.78
     Ganesh
    -0.77
    POSITIVE LOGITS
     South
    1.78
    south
    1.63
    South
    1.61
    SOUTH
    1.59
     south
    1.58
     SOUTH
    1.52
     Southgate
    1.20
     North
    1.12
    north
    1.10
     East
    1.06
    Activations Density 0.080%

    No Known Activations