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

    Neuronpedia

    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. 24-GEMMASCOPE-RES-16K
    11. 4894
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to estimation and statistical methods

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

    Preceding "On" or "of"

    np_acts-logits-general · gemini-2.0-flash

    on [word]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     şun
    -0.48
     např
    -0.47
     solches
    -0.44
     těchto
    -0.43
     belangrij
    -0.43
     takimi
    -0.42
     novedades
    -0.42
     først
    -0.42
     innymi
    -0.41
     lisäksi
    -0.41
    POSITIVE LOGITS
     Walkover
    0.60
     Савезне
    0.60
     brom
    0.59
     betweenstory
    0.57
    GEBURTS
    0.54
    WriteTagHelper
    0.54
     AssemblyProduct
    0.54
    +:+
    0.54
    afro
    0.54
     Kand
    0.53
    Activations Density 0.493%

    No Known Activations