© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10661
    Prev
    Next
    INDEX
    Explanations

    mentions of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mergeFrom
    -0.86
    DeleteBehavior
    -0.80
    ConstraintMaker
    -0.80
     defStyle
    -0.76
    ValueStyle
    -0.75
     TextInputType
    -0.74
     craindre
    -0.73
    FieldBuilder
    -0.72
    IBinder
    -0.71
    ChromeDriver
    -0.71
    POSITIVE LOGITS
     resources
    4.62
     Resources
    3.93
    resources
    3.85
    Resources
    3.75
     resource
    3.73
     RESOURCES
    3.52
     ressources
    3.23
     Resource
    3.12
    resource
    3.11
    RESOURCES
    3.09
    Activations Density 0.061%

    No Known Activations