© 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. 18-GEMMASCOPE-RES-16K
    11. 1677
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and fun

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

    "fun"

    np_acts-logits-general · gemini-2.0-flash

    have fun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.77
     betweenstory
    -0.63
     kohta
    -0.57
     */,
    -0.56
     صوتيه
    -0.52
    ++];
    -0.51
     marquées
    -0.50
     Normdatei
    -0.50
     rédaction
    -0.48
    
    -0.48
    POSITIVE LOGITS
     fun
    2.78
    fun
    2.24
    Fun
    2.13
     Fun
    2.12
     FUN
    2.02
     divertido
    1.79
     enjoyment
    1.78
    FUN
    1.78
     enjoyable
    1.76
     diversión
    1.67
    Activations Density 0.196%

    No Known Activations