© 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. 16-GEMMASCOPE-RES-16K
    11. 6910
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of providing nourishment or sustenance

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

    "feed" and its variations

    np_acts-logits-general · gemini-2.0-flash

    providing sustenance or input

    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
     تضيفلها
    -0.71
    cotch
    -0.71
     Xperia
    -0.67
    uxxxx
    -0.66
    Precalculus
    -0.65
    prefixer
    -0.65
     Μαρ
    -0.64
     colonna
    -0.64
    Capítulo
    -0.62
    erton
    -0.60
    POSITIVE LOGITS
     feeds
    1.58
     feed
    1.57
     Feed
    1.52
     Feeds
    1.44
    feed
    1.43
     FEED
    1.43
    Feed
    1.42
    feeds
    1.37
    FEED
    1.35
     fed
    1.31
    Activations Density 0.120%

    No Known Activations