© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5427
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in a context relating to their roles or relationships

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

    Followed by punctuation or numbers

    np_acts-logits-general · gemini-2.0-flash

    obituary executor Vitals

    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
     perang
    -0.45
    ContentLoaded
    -0.41
    VersionUID
    -0.40
    RequestMapping
    -0.38
     autorytatywna
    -0.36
     scă
    -0.36
    awtextra
    -0.35
    msgTypes
    -0.35
    RegistryLite
    -0.35
     kaikk
    -0.35
    POSITIVE LOGITS
     EconPapers
    0.52
    
    0.51
     obituary
    0.43
     executor
    0.43
     OBITUARY
    0.43
    Vitals
    0.42
     rapporte
    0.42
     Obituary
    0.42
    ſammen
    0.41
    Elevated
    0.41
    Activations Density 0.391%

    No Known Activations