© 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. 15-GEMMASCOPE-RES-16K
    11. 2639
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional responses and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.62
    S
    -0.60
    1
    -0.59
    f
    -0.59
    l
    -0.59
    2
    -0.58
    T
    -0.58
    K
    -0.57
    0
    -0.57
    D
    -0.56
    POSITIVE LOGITS
     pleaſure
    1.27
     myſelf
    1.24
     Anſ
    1.24
     reaſon
    1.21
     ſeveral
    1.20
     purpoſe
    1.19
     himſelf
    1.14
     Houſe
    1.14
    ſelf
    1.13
     ſever
    1.13
    Activations Density 2.760%

    No Known Activations