© 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. 16-GEMMASCOPE-RES-16K
    11. 12935
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific analysis and experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.81
    Personendaten
    -0.79
     CreateTagHelper
    -0.76
     Савезне
    -0.74
    RenderAtEndOf
    -0.73
    LookAnd
    -0.72
     resourceCulture
    -0.71
    曖昧さ回避
    -0.69
     Administrativna
    -0.64
     beginnetje
    -0.63
    POSITIVE LOGITS
     gir
    0.37
     pic
    0.35
     check
    0.35
    外
    0.34
    outer
    0.34
     SOUT
    0.34
     Zu
    0.33
     min
    0.33
     Check
    0.33
     sat
    0.33
    Activations Density 1.265%

    No Known Activations