© 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. 20-GEMMASCOPE-RES-65K
    11. 3486
    Prev
    Next
    INDEX
    Explanations

    references to personal possession and specific locations or contexts related to individuals

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

    introducing specific circumstances

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    tagHelperRunner
    -0.83
     CreateTagHelper
    -0.82
     &___
    -0.75
     متعلقه
    -0.75
    CompleteListener
    -0.74
    rungsseite
    -0.73
    日在
    -0.72
     الحره
    -0.71
    SourceChecksum
    -0.71
    ⓧ
    -0.70
    POSITIVE LOGITS
     context
    0.99
     guise
    0.85
     contexts
    0.84
     vicinity
    0.82
     midst
    0.79
     manner
    0.75
    context
    0.74
     hurry
    0.74
     וב
    0.71
     contesto
    0.70
    Activations Density 0.855%

    No Known Activations