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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15231
    Prev
    Next
    INDEX
    Explanations

    mentions of summer, indicating a focus on seasonal themes

    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
    \]
    -0.71
    Datuak
    -0.68
     Vaticano
    -0.61
    |}{}
    -0.61
     виправивши
    -0.61
    MessageTagHelper
    -0.60
     Leafs
    -0.59
    катери
    -0.58
     Dispose
    -0.57
     Naik
    -0.57
    POSITIVE LOGITS
     Summer
    1.97
     summer
    1.92
    Summer
    1.88
    summer
    1.81
    SUMMER
    1.77
     summertime
    1.73
     SUMMER
    1.71
     summers
    1.52
     Summers
    1.39
     verano
    1.38
    Activations Density 0.019%

    No Known Activations