© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12496
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal reflections and feelings

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

    "I" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    I statements followed by verbs

    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
    NOPQRST
    -0.75
    Interess
    -0.72
    zarchiwizowane
    -0.64
     interest
    -0.64
    Interesting
    -0.62
    })`
    -0.60
     Interesting
    -0.59
    ()]
    
    -0.57
    Lähteet
    -0.56
    jspb
    -0.56
    POSITIVE LOGITS
     hâte
    0.91
     truly
    0.84
     Truly
    0.78
    Truly
    0.76
    truly
    0.75
     absolutely
    0.73
     couldn
    0.71
     verkligen
    0.70
     cherish
    0.69
     menangis
    0.69
    Activations Density 0.170%

    No Known Activations