Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 602
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to classifications, structures, or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoresizingMask
    -0.56
    astify
    -0.52
    keyColumn
    -0.51
    stander
    -0.50
    NSNotification
    -0.49
    bitField
    -0.49
     commentaries
    -0.48
     eventdata
    -0.47
    esterday
    -0.47
    ณ์
    -0.45
    POSITIVE LOGITS
     دیکھیے
    0.56
    webElementXpaths
    0.55
     bénéfices
    0.55
     Paglinawan
    0.52
    OGND
    0.51
     modalités
    0.50
     espagnole
    0.49
     soins
    0.49
     Sakit
    0.48
    ový
    0.47
    Activations Density 0.048%

    No Known Activations