© 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. 9138
    Prev
    Next
    INDEX
    Explanations

    name of locations and people, particularly in political contexts

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

    Abbreviations of months

    np_acts-logits-general · gemini-2.0-flash

    US state abbreviations/names

    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
     Reverend
    -0.58
    Figure
    -0.58
    OwnProperty
    -0.53
     seventeen
    -0.53
     eighteen
    -0.53
     Lieutenant
    -0.51
     twenty
    -0.51
     Figure
    -0.50
     okay
    -0.49
     sólo
    -0.49
    POSITIVE LOGITS
     Sept
    1.14
     Oct
    1.13
     Aug
    1.12
     Fig
    1.10
    Fig
    1.09
     Nov
    1.08
     Feb
    1.07
     Gov
    1.01
     Calif
    0.99
     Jan
    0.99
    Activations Density 0.562%

    No Known Activations