© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 138
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of trees and their ecological characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.86
    MLLoader
    -0.63
    Beh
    -0.61
    PendingIntent
    -0.61
    onAttach
    -0.59
    crollView
    -0.56
    mesis
    -0.56
     cous
    -0.55
     Bianchi
    -0.55
    diali
    -0.54
    POSITIVE LOGITS
     trees
    1.72
     Trees
    1.58
     tree
    1.50
    Trees
    1.42
     Tree
    1.35
     TREES
    1.34
    trees
    1.31
     TREE
    1.30
     forests
    1.26
    Tree
    1.22
    Activations Density 0.338%

    No Known Activations