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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 10120
    Prev
    Next
    INDEX
    Explanations

    the concept of "making" or creating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comigo
    -0.94
    Personensuche
    -0.93
    UTERS
    -0.92
    tagext
    -0.91
    endregion
    -0.89
    MemoryWarning
    -0.88
    GenerationType
    -0.88
     jPanel
    -0.88
    ganggu
    -0.87
    hatian
    -0.86
    POSITIVE LOGITS
    make
    2.25
     make
    2.20
    Make
    2.17
     Make
    2.09
     MAKE
    2.07
    MAKE
    2.05
     made
    2.02
    makes
    1.97
    made
    1.92
    Making
    1.85
    Activations Density 0.139%

    No Known Activations