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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6830
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate legal or judicial processes and outcomes

    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
    RegressionTest
    -0.50
    sizeCache
    -0.50
     NUKAT
    -0.48
    ViewInit
    -0.45
    Spoljašnje
    -0.44
    MessageOf
    -0.42
    帖最后由
    -0.41
    ApiModelProperty
    -0.40
    <?
    -0.39
    WriteBarrier
    -0.38
    POSITIVE LOGITS
     stand
    3.89
     STAND
    3.42
     Stand
    3.38
     stands
    3.38
     stood
    3.22
    Stand
    3.14
    stand
    3.09
     standing
    3.05
     Stands
    2.92
    stands
    2.78
    Activations Density 0.785%

    No Known Activations