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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53301
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing personal responsibility and decision-making

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

    responsibility and creation

    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
    Personendaten
    -0.93
    abestanden
    -0.82
     esternos
    -0.77
    bkz
    -0.73
     propOrder
    -0.69
    
    -0.69
     Италијани
    -0.64
    ագրություններ
    -0.61
    Przypisy
    -0.61
     saites
    -0.60
    POSITIVE LOGITS
    tonode
    0.59
     Савез
    0.54
    TargetException
    0.52
     uș
    0.48
    EndContext
    0.46
    коменду
    0.45
    țion
    0.45
    ințe
    0.44
    AsUp
    0.44
     săptăm
    0.44
    Activations Density 0.129%

    No Known Activations