© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15232
    Prev
    Next
    INDEX
    Explanations

    terms related to cell health and differentiation, particularly focusing on birth defects and cellular processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postmedia
    -0.41
    úly
    -0.38
    /*
    -0.38
    PreAuthorize
    -0.38
    moveToFirst
    -0.36
    etc
    -0.33
    andExpect
    -0.32
    TagHelper
    -0.32
    newswire
    -0.32
    dė
    -0.32
    POSITIVE LOGITS
     called
    3.25
    called
    2.70
     Called
    2.69
    Called
    2.56
     llamado
    2.48
     CALLED
    2.48
     termed
    2.38
     chamado
    2.34
     llamada
    2.33
     nazy
    2.27
    Activations Density 2.401%

    No Known Activations