© 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. 8225
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" in various contexts

    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
     propOrder
    -0.71
     EconPapers
    -0.68
    Pozri
    -0.60
     estimés
    -0.59
    ēju
    -0.58
    vių
    -0.56
    };*/
    -0.54
     }}"></
    -0.54
    hmä
    -0.53
    gisayar
    -0.51
    POSITIVE LOGITS
    join
    2.31
    JOIN
    1.51
    Join
    1.37
     Join
    1.22
     JOIN
    1.20
    joins
    1.17
     join
    1.15
    joining
    1.13
    implode
    1.05
    joined
    0.94
    Activations Density 0.131%

    No Known Activations