© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    expressions of affection and intimacy in relationships

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

    Follows single letters or digits

    np_acts-logits-general · gemini-2.0-flash

    kiss

    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
     personali
    -0.61
    EMPL
    -0.61
     BrowserModule
    -0.61
     ويكي
    -0.60
    </tfoot>
    -0.58
     باخ
    -0.57
     personne
    -0.57
    ंदीखरीदारी
    -0.55
    HomeAsUpEnabled
    -0.55
    发表于
    -0.55
    POSITIVE LOGITS
     kissed
    0.86
     kiss
    0.82
     kisses
    0.81
     bacio
    0.71
     kissing
    0.68
     beijo
    0.65
     Kiss
    0.62
    Kiss
    0.61
    kiss
    0.57
     valentine
    0.55
    Activations Density 0.107%

    No Known Activations