© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1181
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hal" and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -1.05
     Harwood
    -0.83
     Yerevan
    -0.80
    expandindo
    -0.76
     pleaſure
    -0.76
     Madura
    -0.76
     dumne
    -0.76
     nozze
    -0.74
     Pristup
    -0.73
     Somaliland
    -0.73
    POSITIVE LOGITS
     Hal
    1.57
    Hal
    1.38
     hal
    1.33
    hal
    1.27
     HAL
    1.22
     Hub
    1.14
     hub
    1.13
    hub
    1.05
    HAL
    1.05
    Hub
    1.01
    Activations Density 0.063%

    No Known Activations