Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53500
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparedness or readiness

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

    ready for something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.80
     Pollock
    -0.78
     AppCompatTheme
    -0.75
     pinulongan
    -0.75
     Sark
    -0.73
    JNIEnv
    -0.72
    WriteLiteral
    -0.71
    ={`/
    -0.71
     Tib
    -0.68
    Pyx
    -0.67
    POSITIVE LOGITS
     ready
    1.11
     READY
    1.10
    READY
    1.09
     Ready
    1.08
    Ready
    0.96
    ready
    0.86
     sedia
    0.84
     prêts
    0.81
    isReady
    0.78
     prepared
    0.78
    Activations Density 0.013%

    No Known Activations