© 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. 10554
    Prev
    Next
    INDEX
    Explanations

    actions of giving or related concepts, often in a context of selflessness or sacrifice

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

    Forms of the word "give"

    np_acts-logits-general · gemini-2.0-flash

    giving relinquishing things

    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
    SharedCtor
    -0.83
    DrawerLayout
    -0.77
     betweenstory
    -0.71
     المعيارى
    -0.71
     nakalista
    -0.71
    AndEndTag
    -0.69
     resourceCulture
    -0.67
     للمعارف
    -0.66
    uxxxx
    -0.65
    IonicModule
    -0.63
    POSITIVE LOGITS
     rise
    1.21
     birth
    1.04
     GIVE
    1.00
     give
    1.00
     Give
    1.00
    Giving
    0.98
     Giving
    0.98
    Give
    0.97
     credence
    0.96
     Gives
    0.96
    Activations Density 0.142%

    No Known Activations