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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4925
    Prev
    Next
    INDEX
    Explanations

    descriptions of plant morphology and chlorosis attributes

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

    botanical and scientific descriptions of plant characteristics and physiological measurements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ceramby
    -0.46
    PropertyGroup
    -0.46
    DataAnnotations
    -0.45
    ądze
    -0.44
    CrossRef
    -0.44
     skar
    -0.42
    ituitary
    -0.41
     ujednoznacz
    -0.41
    Aiheesta
    -0.41
    bcryptjs
    -0.41
    POSITIVE LOGITS
     leaf
    1.40
     leaves
    1.33
     leafs
    1.20
     Leaf
    1.19
    leaf
    1.16
     Leaves
    1.16
    Leaves
    1.13
    leaves
    1.11
    葉
    1.07
    Leaf
    1.03
    Activations Density 0.249%

    No Known Activations