© 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. 41-GEMMASCOPE-RES-16K
    11. 10047
    Prev
    Next
    INDEX
    Explanations

    key locations and entities related to political and judicial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.38
    ground
    -1.37
    plant
    -1.35
    state
    -1.35
    drive
    -1.34
    rights
    -1.34
    spot
    -1.33
    wind
    -1.33
    power
    -1.33
    light
    -1.33
    POSITIVE LOGITS
     Jr
    0.24
     ​​
    0.20
    . 
    0.17
    .​
    0.17
    .].
    0.17
    ​.
    0.17
    ​,
    0.16
     emeritus
    0.16
    :​
    0.16
    .
    0.15
    Activations Density 0.570%

    No Known Activations