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-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4331
    Prev
    Next
    INDEX
    Explanations

    interactive elements related to user actions in a web interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.59
    StructEnd
    -0.58
    __(/*!
    -0.47
    GOTREF
    -0.46
     otomatig
    -0.44
    NTIS
    -0.44
    verifyException
    -0.44
     Paglinawan
    -0.43
     surla
    -0.43
    AccessFile
    -0.43
    POSITIVE LOGITS
     click
    3.45
     Click
    3.11
    click
    2.92
    Click
    2.89
     clicked
    2.80
     clicking
    2.78
     clicks
    2.75
     CLICK
    2.56
    CLICK
    2.38
     klik
    2.28
    Activations Density 0.691%

    No Known Activations