© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10623
    Prev
    Next
    INDEX
    Explanations

    nature-related terminology and environmental descriptions

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

    Vegetation, woods, or natural landscapes

    np_acts-logits-general · gemini-2.0-flash

    vegetation and natural settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.49
     Administrativna
    -0.45
     HasFactory
    -0.44
    autorest
    -0.44
     capitales
    -0.44
    +#+
    -0.43
     święta
    -0.42
     ostavi
    -0.41
     CreateTagHelper
    -0.41
     avenir
    -0.41
    POSITIVE LOGITS
     bushes
    0.89
     bush
    0.83
     thicket
    0.78
     woodland
    0.76
     shrub
    0.70
     grass
    0.69
     vegetation
    0.68
     wooded
    0.68
     shrubs
    0.68
     brush
    0.66
    Activations Density 0.290%

    No Known Activations