© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 324
    Prev
    Next
    INDEX
    Explanations

    references to thoughtful and romantic gifts, especially within the context of anniversaries or traditional gift-giving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Berge
    -0.55
    شهاد
    -0.55
    ряда
    -0.52
    ništ
    -0.50
    liculas
    -0.49
    GHIJKLM
    -0.48
    enumii
    -0.48
    hdysval
    -0.48
    ApiProperty
    -0.47
    medlem
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.68
    UTERS
    0.67
    stylers
    0.67
    illers
    0.65
    izers
    0.65
     cutters
    0.64
     remo
    0.63
    alers
    0.63
     checkers
    0.62
    fiers
    0.61
    Activations Density 0.925%

    No Known Activations