© 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. 14643
    Prev
    Next
    INDEX
    Explanations

    keywords related to shopping and dietary preferences

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

    ending in "ers," often referring to people/roles

    np_acts-logits-general · gemini-2.0-flash

    groups of people

    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
    classnames
    -0.52
    ")(
    -0.51
    getClass
    -0.48
     Профиль
    -0.47
    avaient
    -0.47
    isesi
    -0.47
     ferme
    -0.47
    ')(
    -0.46
    destroyAll
    -0.46
    Rüyada
    -0.46
    POSITIVE LOGITS
     desiring
    0.66
     desirous
    0.65
     wanting
    0.63
     számára
    0.60
     interested
    0.60
     curieux
    0.57
     wishing
    0.57
     rejoice
    0.56
     travelers
    0.56
     lovers
    0.53
    Activations Density 0.164%

    No Known Activations