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. 10537
    Prev
    Next
    INDEX
    Explanations

    any reference to "Ma" in various forms, indicating a focus on the name or term associated with it

    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
     springfox
    -0.76
    ValueStyle
    -0.72
     Versa
    -0.70
     Ogre
    -0.70
     ogre
    -0.69
    DockStyle
    -0.69
     Hera
    -0.68
     Volga
    -0.68
     Rasa
    -0.67
     Tafel
    -0.65
    POSITIVE LOGITS
     Ma
    2.56
    Ma
    2.42
     ma
    2.32
     MA
    1.94
    ma
    1.81
    MA
    1.73
     Ма
    1.30
     ма
    1.28
    Ма
    1.26
     Mahesh
    1.20
    Activations Density 0.056%

    No Known Activations