© 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. 1-GEMMASCOPE-RES-16K
    11. 2378
    Prev
    Next
    INDEX
    Explanations

    the concept of "level" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 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
    Layer
    -0.90
    layer
    -0.83
     Layer
    -0.74
    layers
    -0.66
     layer
    -0.65
    LAYER
    -0.62
     Layers
    -0.61
     LAYER
    -0.60
     layered
    -0.59
     layers
    -0.58
    POSITIVE LOGITS
    level
    2.44
     level
    2.41
    Level
    2.22
     LEVEL
    2.13
     Level
    2.09
    LEVEL
    2.09
     levels
    1.98
    levels
    1.92
    Levels
    1.83
     Levels
    1.80
    Activations Density 0.204%

    No Known Activations