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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11172
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "msg" in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.78
    SequentialGroup
    -0.78
     BrowserRouter
    -0.75
     Stande
    -0.73
    branche
    -0.73
    Посилання
    -0.71
    nere
    -0.71
    CUB
    -0.70
    ]--;
    -0.70
    Билгалдахарш
    -0.68
    POSITIVE LOGITS
    msg
    1.83
     msg
    1.78
     Msg
    1.24
    getMsg
    1.18
    setMsg
    1.17
    Msg
    1.17
     msgs
    1.07
    Msgs
    1.04
    MSG
    1.04
     MSG
    0.91
    Activations Density 0.070%

    No Known Activations