© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11682
    Prev
    Next
    INDEX
    Explanations

    references to change and its various impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.59
    rovnik
    -0.57
    éma
    -0.52
    ReusableCell
    -0.50
    ToPoint
    -0.46
    Initializable
    -0.45
     Ngb
    -0.45
    AndroidJUnit
    -0.45
    CloseOperation
    -0.45
     Roskov
    -0.44
    POSITIVE LOGITS
     changing
    1.27
     changed
    1.24
     change
    1.24
     Changing
    1.18
    Changing
    1.17
     changer
    1.16
     CHANG
    1.14
     Changed
    1.14
     Change
    1.13
    changing
    1.11
    Activations Density 0.789%

    No Known Activations