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. 8-GEMMASCOPE-RES-16K
    6. 5628
    Prev
    Next
    INDEX
    Explanations

    references to mice and related activities in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.89
     Amon
    -0.77
    المناصب
    -0.72
    Сере
    -0.71
    లాలు
    -0.69
    ţele
    -0.69
    #
    -0.69
    !";
    -0.68
     =",
    -0.68
    ?";
    -0.68
    POSITIVE LOGITS
     Mouse
    2.08
     mouse
    2.04
     mice
    1.94
     Mice
    1.87
     MOUSE
    1.80
    Mouse
    1.75
    mouse
    1.74
    Mice
    1.67
    MOUSE
    1.66
    mice
    1.60
    Activations Density 0.093%

    No Known Activations