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. 13502
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "make" in various forms and contexts

    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
    KommentareTeilen
    -0.74
    ActionCreators
    -0.70
    aronder
    -0.69
    uminense
    -0.68
    RUnlock
    -0.67
    riezmann
    -0.66
    endpush
    -0.65
     getopt
    -0.65
     aapt
    -0.65
     kasarigan
    -0.65
    POSITIVE LOGITS
     Make
    1.19
     make
    1.14
    Make
    1.06
     MAKE
    1.05
     makes
    0.95
     Made
    0.94
    Made
    0.91
     making
    0.91
     made
    0.89
     Makes
    0.87
    Activations Density 0.197%

    No Known Activations