© 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. 23-GEMMASCOPE-RES-16K
    6. 9945
    Prev
    Next
    INDEX
    Explanations

    biographical details about individuals, especially concerning their history and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.72
    bigsqcup
    -0.69
    ChildIndex
    -0.65
    OGND
    -0.61
     vPvB
    -0.60
     BorderSide
    -0.59
    PRWEB
    -0.59
    NewRow
    -0.58
     caufe
    -0.57
     PicClick
    -0.57
    POSITIVE LOGITS
     lifetime
    0.64
     member
    0.51
     retired
    0.50
    Lifetime
    0.50
     lifelong
    0.50
     twier
    0.49
    原始内容存档于
    0.48
    lifetime
    0.47
    ográ
    0.47
    FileSystem
    0.47
    Activations Density 0.085%

    No Known Activations