© 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. 1839
    Prev
    Next
    INDEX
    Explanations

    sentences expressing opinions or political commentary regarding actions and behavior of individuals or groups

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

    following "would", "to", or "will"

    np_acts-logits-general · gemini-2.0-flash

    would make

    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
    ourne
    -0.57
     partecipare
    -0.46
     Paglinawan
    -0.44
     Constant
    -0.44
    bav
    -0.44
     Kirke
    -0.42
    といけない
    -0.42
    HOUT
    -0.42
    Constant
    -0.42
    насе
    -0.42
    POSITIVE LOGITS
     lenker
    0.93
     relent
    0.84
     cave
    0.76
     caves
    0.75
     realizes
    0.74
     capit
    0.74
     listens
    0.72
     listened
    0.72
     يتيمه
    0.70
     backed
    0.70
    Activations Density 0.363%

    No Known Activations