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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 28078
    Prev
    Next
    INDEX
    Explanations

    specific references to recommending services

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

    real estate professional needs

    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
     propOrder
    -0.61
    ustimmung
    -0.57
    BeginContext
    -0.54
    Sucesor
    -0.53
     AttributeSet
    -0.52
    psack
    -0.49
    Geplaatst
    -0.49
    antwortung
    -0.48
    unesse
    -0.48
    ounid
    -0.46
    POSITIVE LOGITS
     Needed
    0.67
     needed
    0.65
    featureID
    0.63
    ollectionView
    0.61
    Needed
    0.60
    Need
    0.60
    needed
    0.60
     any
    0.60
     needs
    0.60
     entrusted
    0.59
    Activations Density 0.035%

    No Known Activations