© 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. 16-GEMMASCOPE-RES-16K
    6. 5759
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and indictments

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

    Punctuation followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    verbs following specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depended
    -1.03
     consisted
    -1.00
     differed
    -0.98
     wore
    -0.97
     resembled
    -0.94
     was
    -0.92
     lacked
    -0.92
     flowed
    -0.92
     amounted
    -0.91
    knew
    -0.90
    POSITIVE LOGITS
     becomes
    0.74
     gets
    0.70
     arrives
    0.70
     decides
    0.69
     begins
    0.67
     goes
    0.67
     comes
    0.65
     takes
    0.61
     realizes
    0.60
     opens
    0.59
    Activations Density 0.478%

    No Known Activations