© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10765
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving and providing

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

    "give" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    give to someone or something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     umane
    -0.61
    يميديا
    -0.60
    Hvordan
    -0.58
     femmin
    -0.56
    SourceChecksum
    -0.51
    <bos>
    -0.51
     sapere
    -0.50
    ArgsConstructor
    -0.50
     pubblici
    -0.48
     vapeur
    -0.48
    POSITIVE LOGITS
     them
    1.00
     me
    0.96
     us
    0.91
     him
    0.81
     you
    0.80
    them
    0.67
    ]--;
    0.66
     everyone
    0.62
     everybody
    0.61
    give
    0.59
    Activations Density 0.191%

    No Known Activations