© 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. 15-GEMMASCOPE-RES-16K
    11. 592
    Prev
    Next
    INDEX
    Explanations

    specific references to sections or examples within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.71
     Numerade
    -0.71
     lenker
    -0.68
    SequentialGroup
    -0.65
    SPATH
    -0.64
    WriteTagHelper
    -0.64
    AndroidJUnit
    -0.61
    abestanden
    -0.60
    principalColumn
    -0.60
     Biôgrafia
    -0.59
    POSITIVE LOGITS
     OF
    0.30
    ⏟
    0.30
    Previous
    0.30
     précédent
    0.28
    course
    0.27
    Kanpo
    0.27
    miştir
    0.26
    reiches
    0.26
    Two
    0.26
    Hotel
    0.26
    Activations Density 1.578%

    No Known Activations