© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    key phrases that imply user preferences or experiences, particularly regarding media and technology

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

    preceding "normal"

    np_acts-logits-general · gemini-2.0-flash

    normal or nearly normal

    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
     GenerationType
    -0.81
    setVerticalGroup
    -0.59
    czegó
    -0.57
    wäh
    -0.56
     EconPapers
    -0.55
    brigens
    -0.54
     propOrder
    -0.53
     récente
    -0.52
    urably
    -0.52
    TableBody
    -0.51
    POSITIVE LOGITS
     normal
    3.64
    normal
    3.18
    Normal
    2.90
     normale
    2.82
     Normal
    2.76
     usual
    2.70
     NORMAL
    2.68
     ordinary
    2.65
     normalen
    2.62
     normales
    2.62
    Activations Density 1.159%

    No Known Activations