© 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. 16324
    Prev
    Next
    INDEX
    Explanations

    terms related to agriculture and community-supported agriculture programs

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

    Oregon or Portland

    np_acts-logits-general · gemini-2.0-flash

    Oregon cities and regions

    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
    clerview
    -0.59
     Ludwig
    -0.58
    
    -0.56
    lawayo
    -0.54
     Warrington
    -0.53
    ResponseEntity
    -0.53
     Hogarth
    -0.52
    ähkö
    -0.52
    </caption>
    -0.52
    <?
    -0.52
    POSITIVE LOGITS
     Oregon
    1.27
     Portland
    1.15
    Oregon
    1.13
     OREGON
    1.08
     oregon
    1.05
    oregon
    1.05
    Portland
    1.01
     Mult
    0.95
     Willa
    0.90
    Mult
    0.83
    Activations Density 0.123%

    No Known Activations