© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 120242
    Prev
    Next
    INDEX
    Explanations

    terms related to hobbies and interests

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

    hobby or interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ҭ
    -0.49
    forza
    -0.45
    tedì
    -0.43
    }]
    
    -0.41
     facie
    -0.40
     rep
    -0.39
     Rolls
    -0.39
    有效
    -0.38
    有力
    -0.38
    uolo
    -0.38
    POSITIVE LOGITS
     hobbies
    1.39
     Hobbies
    1.07
    Hobbies
    1.01
     passions
    0.79
    趣味
    0.67
     leisure
    0.66
     pursuits
    0.63
     loisirs
    0.62
    Datuak
    0.60
    Leisure
    0.59
    Activations Density 0.003%

    No Known Activations