© 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. 24-GEMMASCOPE-RES-16K
    11. 8007
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the name "Hal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "Hal" or "HAL"

    np_acts-logits-general · gemini-2.0-flash

    Haloid, Halliburton, haloperidol, Haldex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esModule
    -0.67
    //</
    -0.59
     <=",
    -0.57
     broad
    -0.52
    setVerticalGroup
    -0.52
    AutoField
    -0.51
    ettet
    -0.51
    Hozzáférés
    -0.50
    DatabaseError
    -0.50
    principalTable
    -0.49
    POSITIVE LOGITS
    InitVars
    0.75
    \{\\
    0.68
     Roskov
    0.60
     Савезне
    0.59
    lujah
    0.59
    cyon
    0.58
    ArrowToggle
    0.57
    libur
    0.57
    Хьажоргаш
    0.55
     Paglinawan
    0.54
    Activations Density 0.143%

    No Known Activations