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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9002
    Prev
    Next
    INDEX
    Explanations

    discussions or actions related to change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewDidLoad
    -0.47
     LoggerFactory
    -0.47
     Seelen
    -0.46
    autogui
    -0.46
     nakalista
    -0.46
     >&
    -0.44
     proficient
    -0.43
     AssemblyTitle
    -0.43
    AndroidJUnit
    -0.42
    quirrels
    -0.42
    POSITIVE LOGITS
     Change
    1.29
    Change
    1.27
    change
    1.26
     change
    1.24
    CHANGE
    1.19
     CHANGE
    1.15
     Changer
    1.05
    Changing
    1.01
     Changed
    0.98
    Changer
    0.97
    Activations Density 0.137%

    No Known Activations