© 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. 0-GEMMASCOPE-RES-16K
    11. 7992
    Prev
    Next
    INDEX
    Explanations

    contexts that involve customization and custom-defined parameters or fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.52
    ActionCreators
    -0.50
    ngdoc
    -0.44
    AutoScaleMode
    -0.40
    UnitTesting
    -0.39
    httphttps
    -0.38
     mView
    -0.38
    WriteBarrier
    -0.37
    throughout
    -0.37
     viewDidLoad
    -0.36
    POSITIVE LOGITS
     Customization
    0.62
     customization
    0.60
     suffix
    0.58
     Wizard
    0.57
    Customization
    0.57
     custom
    0.56
     customize
    0.54
     Veterin
    0.54
     Root
    0.53
     Shr
    0.53
    Activations Density 1.689%

    No Known Activations