© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30963
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and references within the text

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

    subsequently perform

    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
     AttributeSet
    -0.60
     suspensão
    -0.56
     réunions
    -0.55
    guien
    -0.54
     autorytatywna
    -0.54
    voorbeeld
    -0.54
    ătoare
    -0.54
     stället
    -0.54
    árs
    -0.52
     exemples
    -0.52
    POSITIVE LOGITS
    帖最后由
    0.51
    OGND
    0.47
     Nanos
    0.45
     protoimpl
    0.45
     tiế
    0.44
     comis
    0.43
    RTEE
    0.43
     DBNull
    0.43
     satisfaction
    0.43
     %).
    0.42
    Activations Density 0.470%

    No Known Activations