© 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. 28-GEMMASCOPE-RES-16K
    11. 9511
    Prev
    Next
    INDEX
    Explanations

    key points related to emotional expressions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "that," "how," or "due."

    np_acts-logits-general · gemini-2.0-flash

    introduces explanations or reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    今回も
    -0.37
    NSIndexPath
    -0.36
    zystać
    -0.34
    zkopf
    -0.33
    TestFixture
    -0.33
     IndexPath
    -0.33
    BASEPATH
    -0.32
     professione
    -0.32
    pillars
    -0.32
     estimé
    -0.32
    POSITIVE LOGITS
     how
    0.74
     faptul
    0.71
     its
    0.65
    LookAnd
    0.60
    ValueStyle
    0.58
     kaarangay
    0.56
    ImageContext
    0.54
    aarrggbb
    0.54
    RegressionTest
    0.54
     unwillingness
    0.53
    Activations Density 0.627%

    No Known Activations