© 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. 9-GEMMASCOPE-RES-16K
    11. 1796
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "two" and its associated numerical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -1.05
     vaisselle
    -0.77
    mer
    -0.70
    er
    -0.66
    čaj
    -0.64
     QLD
    -0.64
    mente
    -0.62
     argint
    -0.61
     ČR
    -0.60
    ñores
    -0.60
    POSITIVE LOGITS
     Two
    1.17
     CreateTagHelper
    1.11
     two
    1.10
    Према
    1.09
     dozen
    1.09
    TWO
    1.08
    Two
    1.08
     TWO
    1.07
    aarrggbb
    0.99
    two
    0.99
    Activations Density 0.160%

    No Known Activations