© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6458
    Prev
    Next
    INDEX
    Explanations

    phrases discussing medical conditions and patient safety regarding medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.48
     sitesinde
    -0.47
    createView
    -0.38
    Espèce
    -0.38
    Junior
    -0.38
    Cyfarwyddwr
    -0.37
    roep
    -0.36
     článku
    -0.36
     kı
    -0.35
    actu
    -0.35
    POSITIVE LOGITS
     Conſ
    0.51
     ſtate
    0.46
    tagHelperRunner
    0.46
    wiſe
    0.45
    execSQL
    0.44
     Diſ
    0.43
    GIVEREF
    0.43
    findpost
    0.42
     uſe
    0.41
     nahilalakip
    0.41
    Activations Density 0.442%

    No Known Activations