Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13710
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "join."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.65
    schmidt
    -0.60
     presup
    -0.55
    erokee
    -0.51
    ORAGE
    -0.50
    parsedMessage
    -0.50
    chera
    -0.50
     خارجية
    -0.50
    </thead>
    -0.50
     Haram
    -0.49
    POSITIVE LOGITS
     join
    4.81
     joining
    4.24
     joins
    4.18
     Join
    4.14
    join
    4.05
    Join
    4.03
     joined
    3.94
     JOIN
    3.93
     Joining
    3.80
    JOIN
    3.64
    Activations Density 0.065%

    No Known Activations