© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10169
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize uniqueness and originality

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

    "unique"

    np_acts-logits-general · gemini-2.0-flash

    unique, one of a kind

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    chism
    -0.54
     SwitchCompat
    -0.49
    olarmente
    -0.45
    xase
    -0.45
    windowFixed
    -0.45
     lenker
    -0.44
     ImportError
    -0.43
    égias
    -0.43
    antaine
    -0.43
     OMITTED
    -0.42
    POSITIVE LOGITS
     unique
    1.09
     uniqueness
    0.97
     Unique
    0.96
    Unique
    0.94
     uniques
    0.88
    unique
    0.88
     unieke
    0.88
     UNIQUE
    0.86
     einzigartige
    0.80
    UNIQUE
    0.78
    Activations Density 0.277%

    No Known Activations