© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6163
    Prev
    Next
    INDEX
    Explanations

    monetary values and their associated attributes in different contexts

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

    Follows a colon

    np_acts-logits-general · gemini-2.0-flash

    none

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.81
    archiviato
    -0.74
    tagext
    -0.70
     imageNamed
    -0.65
     IBOutlet
    -0.62
    =#{
    -0.60
    醐
    -0.58
    AddTagHelper
    -0.57
     getItemId
    -0.57
     endwhile
    -0.56
    POSITIVE LOGITS
     None
    1.26
     none
    1.12
    None
    1.07
    none
    1.02
      
    0.92
     The
    0.91
    NONE
    0.88
     NONE
    0.84
     なし
    0.80
     This
    0.77
    Activations Density 0.443%

    No Known Activations