© 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. 22-GEMMASCOPE-RES-16K
    6. 13684
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rose" in various contexts

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

    "Rose" and variations

    np_acts-logits-general · gemini-2.0-flash

    Rose as a name or the flower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kaieteur
    -0.59
     ihop
    -0.58
    Forums
    -0.58
     ErrIntOverflow
    -0.57
     comuniques
    -0.54
     Speicher
    -0.54
    safe
    -0.54
    putAll
    -0.53
    tzmann
    -0.53
     Lombard
    -0.53
    POSITIVE LOGITS
     petals
    1.13
     petal
    0.93
    marie
    0.73
     blooms
    0.72
    Roses
    0.70
     bloom
    0.69
     Petal
    0.68
    petal
    0.68
    buds
    0.68
    🌹
    0.68
    Activations Density 0.112%

    No Known Activations