© 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. 20-GEMMASCOPE-RES-16K
    11. 4255
    Prev
    Next
    INDEX
    Explanations

    scientific names and classifications of plant species

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

    scientific names of biological species, particularly taxonomic notation with Latin names.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    niſſe
    -0.68
    principalColumn
    -0.65
     MainAxisSize
    -0.65
    ロウィン
    -0.61
    Rüyada
    -0.60
     CreateTagHelper
    -0.60
     reaſon
    -0.59
     queſto
    -0.59
     Biôgrafia
    -0.59
     ويكيپ
    -0.58
    POSITIVE LOGITS
     og
    0.36
     آم
    0.31
    StackNavigator
    0.31
     Hef
    0.31
    เ
    0.30
    astify
    0.29
     Meksiku
    0.29
     al
    0.28
     Flan
    0.28
    kan
    0.28
    Activations Density 0.055%

    No Known Activations