© 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. 4-GEMMASCOPE-RES-16K
    11. 16242
    Prev
    Next
    INDEX
    Explanations

    terms related to intimate physical interactions and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AfterViewInit
    -0.51
    riert
    -0.50
     capito
    -0.49
     préférences
    -0.47
     ögon
    -0.46
     OBS
    -0.46
    StandardCharsets
    -0.46
    オー
    -0.45
    sify
    -0.45
    IConfiguration
    -0.45
    POSITIVE LOGITS
     kiss
    1.44
     kisses
    1.31
     kissed
    1.29
     kissing
    1.27
     touching
    1.23
     touch
    1.22
     touched
    1.17
     touches
    1.16
    kiss
    1.14
     Kiss
    1.12
    Activations Density 0.371%

    No Known Activations