© 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. 3-GEMMASCOPE-RES-16K
    11. 15916
    Prev
    Next
    INDEX
    Explanations

    structures or forms related to towers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phosa
    -0.77
     propOrder
    -0.72
     biais
    -0.71
     BioLib
    -0.70
    esgue
    -0.68
     McKinnon
    -0.64
    awakeFromNib
    -0.63
     dục
    -0.63
    Vidite
    -0.63
    ptonshire
    -0.63
    POSITIVE LOGITS
     tower
    3.27
     Tower
    3.22
     TOWER
    2.98
    Tower
    2.98
     towers
    2.92
    tower
    2.88
     Towers
    2.60
    towers
    2.36
     torre
    2.03
    タワー
    1.75
    Activations Density 0.069%

    No Known Activations