© 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. 6171
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "slides" and "sliding" in various contexts

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

    "slide" and its variations

    np_acts-logits-general · gemini-2.0-flash

    slide / sliding movement

    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
    NameInMap
    -0.66
    Portail
    -0.56
    -------
    -0.54
    transQ
    -0.52
    WebElementEntity
    -0.51
     stanovnika
    -0.48
    complexType
    -0.41
    !*\
    -0.39
     raiſ
    -0.38
    getFullYear
    -0.37
    POSITIVE LOGITS
     slide
    1.19
     Slide
    1.04
    slide
    1.02
     slides
    1.00
     sliding
    0.98
     slid
    0.96
    Slide
    0.93
     Sliding
    0.93
     slider
    0.87
    Sliding
    0.83
    Activations Density 0.184%

    No Known Activations