© 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. 12589
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and affiliations in sports and governance contexts

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

    followed by "in"

    np_acts-logits-general · gemini-2.0-flash

    places followed by city name

    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
     kasarigan
    -1.11
     nakalista
    -1.09
    ंदीखरीदारी
    -1.08
    rungsseite
    -1.04
     betweenstory
    -1.03
     estekak
    -1.01
    Personensuche
    -1.01
     تضيفلها
    -0.99
     חיצוניים
    -0.99
     الرياضيه
    -0.99
    POSITIVE LOGITS
     
    0.66
    ฯ
    0.63
    ,
    0.54
    -
    0.50
     as
    0.50
    DOCTYPE
    0.49
     in
    0.48
    CONTINUE
    0.48
     de
    0.47
     an
    0.47
    Activations Density 0.499%

    No Known Activations