© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2524
    Prev
    Next
    INDEX
    Explanations

    terms related to marine environments and scuba diving activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impeachment
    -0.54
     disambiguazione
    -0.52
     pinulongan
    -0.52
    "}")
    -0.49
    >())
    -0.49
    wapV
    -0.48
    alberto
    -0.48
    enschaften
    -0.47
     jScrollPane
    -0.46
    })));
    -0.46
    POSITIVE LOGITS
     reefs
    0.86
     underwater
    0.85
    underwater
    0.83
     dive
    0.80
     Underwater
    0.75
     reef
    0.74
     diving
    0.74
     Diving
    0.73
    Diving
    0.73
     snork
    0.73
    Activations Density 0.282%

    No Known Activations