© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6033
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements and alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.85
    SourceChecksum
    -0.83
    AccessorTable
    -0.82
    Tikang
    -0.78
    GEBURTSDATUM
    -0.77
    تقاوى
    -0.76
     Administrativna
    -0.75
     kasarigan
    -0.75
     ProtoMessage
    -0.75
     Италијани
    -0.72
    POSITIVE LOGITS
     recently
    0.40
     and
    0.40
     
    0.34
    "
    0.33
     recientemente
    0.33
    PyExc
    0.33
    recently
    0.32
    '
    0.32
     remercier
    0.31
     допомогти
    0.31
    Activations Density 0.517%

    No Known Activations