© 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. 2-GEMMASCOPE-RES-16K
    11. 14907
    Prev
    Next
    INDEX
    Explanations

    instances of the word "joined" indicating a sense of affiliation or teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknowns
    -0.53
    <table>
    -0.52
     wounds
    -0.51
    NoSuch
    -0.50
     Extr
    -0.50
     שכ
    -0.50
     matur
    -0.50
     keuken
    -0.50
     evapor
    -0.50
     Solu
    -0.49
    POSITIVE LOGITS
     joined
    1.74
     Joined
    1.69
    Joined
    1.63
    joined
    1.45
    Joining
    1.11
     attended
    1.11
     Joining
    1.08
     rejoined
    1.06
    attended
    0.96
    joining
    0.94
    Activations Density 0.219%

    No Known Activations