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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8220
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts that emphasize quantity or collective aspects

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

    "all", "every," "any," or "much"

    np_acts-logits-general · gemini-2.0-flash

    all the time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </>
    -0.70
     $_"
    -0.70
    niająca
    -0.67
     للاسماء
    -0.67
     '',
    -0.64
    ządu
    -0.64
    betical
    -0.63
     "",
    -0.63
     Verſ
    -0.63
    StoryboardSegue
    -0.62
    POSITIVE LOGITS
    mybatisplus
    0.65
     nakalista
    0.47
     way
    0.44
    verwijspagina
    0.44
     secara
    0.43
    ða
    0.43
    DatabaseError
    0.42
    RegressionTest
    0.42
     steder
    0.42
     allá
    0.41
    Activations Density 0.511%

    No Known Activations