© 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. 5493
    Prev
    Next
    INDEX
    Explanations

    words related to assessment and awareness of conditions or scenarios

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

    preceding "than"

    np_acts-logits-general · gemini-2.0-flash

    identifying comparisons of "more than"

    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
     enough
    -0.45
    まま
    -0.43
    GenerationType
    -0.42
     very
    -0.42
    ModelAttribute
    -0.42
    足够
    -0.40
     makeStyles
    -0.40
     архивлан
    -0.40
    charCode
    -0.39
     mostly
    -0.39
    POSITIVE LOGITS
     than
    2.17
     THAN
    1.52
    than
    1.51
     niż
    1.49
    Than
    1.48
    THAN
    1.25
     Than
    1.24
     než
    1.23
     än
    1.09
     ніж
    0.94
    Activations Density 0.583%

    No Known Activations