© 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. 15424
    Prev
    Next
    INDEX
    Explanations

    references to auditory perception or communication

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

    "hearing" or "heard."

    np_acts-logits-general · gemini-2.0-flash

    hearing voices and reports

    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
    SharedDtor
    -0.52
    ništvo
    -0.50
    uskas
    -0.50
    Bibliografía
    -0.48
     Picchu
    -0.47
     Vikipedi
    -0.47
    sequelize
    -0.47
    Seni
    -0.47
    LookUp
    -0.47
     TextAppearance
    -0.46
    POSITIVE LOGITS
    tedly
    0.90
     voices
    0.89
     rumors
    0.86
    👂
    0.85
     parler
    0.83
     whispers
    0.83
     rumours
    0.80
     atenta
    0.78
     hears
    0.77
     stories
    0.77
    Activations Density 0.058%

    No Known Activations