© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7582
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to disproportionality or excessiveness

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

    followed by "ate" or "ately."

    np_acts-logits-general · gemini-2.0-flash

    disproportionate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.74
    ust
    -0.47
    ęki
    -0.46
    romyalgia
    -0.45
    AllowUser
    -0.44
     vallée
    -0.44
     vest
    -0.42
    STT
    -0.42
    sillon
    -0.42
     Aps
    -0.42
    POSITIVE LOGITS
    ate
    1.49
    ATE
    1.33
    ates
    1.13
    ATES
    1.05
    ately
    1.05
    rate
    1.05
     ate
    1.02
    Ate
    1.01
    atea
    0.96
    ateness
    0.95
    Activations Density 0.396%

    No Known Activations