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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13225
    Prev
    Next
    INDEX
    Explanations

    references to historical events or figures

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

    "History" or a similar variation

    np_acts-logits-general · gemini-2.0-flash

    history and historical accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.90
    Chham
    -0.72
     himſelf
    -0.70
     nahilalakip
    -0.68
     myſelf
    -0.66
     theſe
    -0.66
     Infantil
    -0.66
     themſelves
    -0.65
     WaitForSeconds
    -0.64
     poffible
    -0.64
    POSITIVE LOGITS
     useHistory
    0.70
    چه
    0.68
     books
    0.64
     болезни
    0.57
     panjang
    0.55
    prepareStatement
    0.55
    ymce
    0.55
     lesson
    0.53
     boyunca
    0.53
    悠
    0.52
    Activations Density 0.126%

    No Known Activations