© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3836
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or searching for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     search
    -0.56
     CURIAM
    -0.54
     InputDecoration
    -0.54
     hunt
    -0.54
     informée
    -0.53
     typelib
    -0.50
    ($__
    -0.46
     AsyncTask
    -0.45
    makeText
    -0.45
    GEBURTS
    -0.45
    POSITIVE LOGITS
     searching
    1.66
     seeking
    1.65
     trying
    1.45
    searching
    1.44
    seeking
    1.41
     hoping
    1.39
     Seeking
    1.38
    Seeking
    1.38
     Searching
    1.35
    Searching
    1.34
    Activations Density 0.116%

    No Known Activations