© 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. 38-GEMMASCOPE-RES-16K
    11. 8888
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to nature and scenic landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.49
     brevet
    -0.47
     location
    -0.43
    location
    -0.40
    enderror
    -0.38
    paramref
    -0.36
    最強
    -0.36
    xcf
    -0.35
     reverse
    -0.35
    AppRoutingModule
    -0.34
    POSITIVE LOGITS
     trees
    0.83
     rows
    0.74
     fountains
    0.73
     greenery
    0.71
     bushes
    0.69
     tall
    0.69
     lawns
    0.69
     wildflowers
    0.68
     alberi
    0.68
     shrubs
    0.68
    Activations Density 0.358%

    No Known Activations