© 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. 14620
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to the position of deputy in various contexts

    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
    urlopen
    -0.63
    forName
    -0.63
    forRoot
    -0.57
    Morrison
    -0.56
    ANTLR
    -0.52
    featureID
    -0.52
    URLException
    -0.50
    zzleHttp
    -0.50
    useNewUrlParser
    -0.48
    contentValues
    -0.48
    POSITIVE LOGITS
     deputy
    0.74
     assistant
    0.71
     Deputy
    0.66
     Vice
    0.64
     vice
    0.63
     Assistant
    0.61
     chief
    0.60
    PUTY
    0.58
    Assistant
    0.56
     Chief
    0.56
    Activations Density 0.172%

    No Known Activations