© 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. 11419
    Prev
    Next
    INDEX
    Explanations

    references to the concept of doing everything or anything possible

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

    "everything" or "anything" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    everything, anything, all

    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
    RetentionPolicy
    -0.45
    SequentialGroup
    -0.44
    tanleria
    -0.42
    dehydes
    -0.42
     constituents
    -0.41
    choly
    -0.41
    ประ
    -0.41
    daß
    -0.40
     arşivlendi
    -0.40
    angliski
    -0.40
    POSITIVE LOGITS
    everything
    1.13
     everything
    1.12
     Everything
    1.03
    Everything
    1.02
     EVERYTHING
    0.95
     tudo
    0.75
     Tudo
    0.65
     alles
    0.62
    一切
    0.60
    的一切
    0.60
    Activations Density 0.324%

    No Known Activations