© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4978
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing importance or significance

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

    "It was" or past tense narration

    np_acts-logits-general · gemini-2.0-flash

    positive adjectives before clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    currently
    -0.68
     currently
    -0.62
     now
    -0.61
     '\\;'
    -0.60
     Currently
    -0.59
    Currently
    -0.59
     sekarang
    -0.59
     Administrativna
    -0.59
     obecnie
    -0.59
     actuellement
    -0.57
    POSITIVE LOGITS
     originally
    0.79
     previously
    0.63
     originalmente
    0.63
     Originally
    0.60
    Originally
    0.58
    originally
    0.58
     initially
    0.57
     yesterday
    0.57
     earlier
    0.56
     ayer
    0.56
    Activations Density 1.061%

    No Known Activations