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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1611
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

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

    Numbers that follow a hyphen

    np_acts-logits-general · gemini-2.0-flash

    solving mathematical equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     "..\..\
    -0.46
    uxxxx
    -0.44
    Ngh
    -0.41
     aang
    -0.36
     Савезне
    -0.35
     נת
    -0.35
    errat
    -0.35
    ArrowToggle
    -0.34
     katal
    -0.34
    CRIP
    -0.34
    POSITIVE LOGITS
    AntiForgeryToken
    0.57
    Filmographie
    0.55
     plátano
    0.53
     chofe
    0.49
     Italijani
    0.48
    MemoryWarning
    0.46
     contextLoads
    0.43
     nakalista
    0.43
    最快更新
    0.42
     endforeach
    0.42
    Activations Density 0.146%

    No Known Activations