© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2688
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and family dynamics

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

    Names followed by family relations

    np_acts-logits-general · gemini-2.0-flash

    names of people and siblings

    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
    DockStyle
    -0.81
     MainAxisSize
    -0.56
    IntoConstraints
    -0.56
    原始内容存档于
    -0.55
    MLLoader
    -0.54
    SpringBootTest
    -0.54
    argout
    -0.53
     Мексичка
    -0.52
    +#+#
    -0.52
     doInBackground
    -0.51
    POSITIVE LOGITS
     Lat
    0.68
     Ras
    0.66
     Marquis
    0.65
     Ke
    0.65
     Lamont
    0.63
     Tyrone
    0.63
     Sha
    0.62
     Ty
    0.61
    Sha
    0.60
     Jam
    0.60
    Activations Density 0.143%

    No Known Activations