© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9577
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" and its variations, indicating a focus on collaboration or gathering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.67
    eficent
    -0.56
    __*/
    -0.56
     StatefulWidget
    -0.54
    ándolos
    -0.54
    GenerationType
    -0.53
     }}}
    -0.53
    EndContext
    -0.53
    GHIJKLM
    -0.53
     deh
    -0.52
    POSITIVE LOGITS
     join
    1.04
     Join
    1.02
     joins
    0.94
     joined
    0.94
    Join
    0.92
    JOIN
    0.91
     JOIN
    0.89
     joining
    0.87
    Joining
    0.87
    join
    0.86
    Activations Density 0.212%

    No Known Activations