© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126771
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating enjoyable experiences

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

    enjoyment and pleasant experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.59
    ciple
    -0.53
     שוליים
    -0.51
    gucig
    -0.50
     plurality
    -0.50
     permeable
    -0.49
    momix
    -0.48
    Weaknesses
    -0.46
    tiérrez
    -0.46
     estekak
    -0.44
    POSITIVE LOGITS
     enjoyment
    0.50
    astify
    0.42
     <<<<<<<<<<<<<<
    0.41
     enjoyable
    0.40
    MessageOf
    0.38
    recated
    0.38
     experiences
    0.37
    enjoy
    0.37
     enjoyed
    0.37
     experience
    0.35
    Activations Density 0.011%

    No Known Activations