© 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. 20-GEMMASCOPE-RES-16K
    11. 14421
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and details related to rainfall and precipitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific measurement instruments and data collection devices, particularly weather and environmental monitoring equipment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.52
    NgModule
    -0.43
    TextAppearance
    -0.42
     NgModule
    -0.40
     AppModule
    -0.40
    mybatis
    -0.40
    ScopeManager
    -0.38
     cervello
    -0.38
    stateProvider
    -0.38
     ome
    -0.37
    POSITIVE LOGITS
     sampling
    0.60
     samples
    0.58
     sampled
    0.57
     betweenstory
    0.54
    sampled
    0.54
     measurements
    0.54
     monitoring
    0.54
     station
    0.53
    sampling
    0.51
     Proben
    0.51
    Activations Density 0.256%

    No Known Activations