© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5589
    Prev
    Next
    INDEX
    Explanations

    phrases related to mating systems and reproductive behaviors

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

    associated with primates

    np_acts-logits-general · gemini-2.0-flash

    primates and monkeys

    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
    alleye
    -0.55
     Lia
    -0.51
     Perse
    -0.51
    providedIn
    -0.50
     waterfowl
    -0.50
     bayern
    -0.50
    casting
    -0.50
     Unic
    -0.49
    Poul
    -0.49
     Egg
    -0.49
    POSITIVE LOGITS
     chimp
    1.17
     monkey
    1.15
     primate
    1.13
     chimpanze
    1.13
     monkeys
    1.11
     apes
    1.08
     primates
    1.08
     Ape
    1.07
     Apes
    1.07
     Monkey
    1.07
    Activations Density 0.274%

    No Known Activations