© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12708
    Prev
    Next
    INDEX
    Explanations

    references to marine environments and organisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guanajuato
    -0.47
     BrowserModule
    -0.47
    Tikang
    -0.43
    群馬
    -0.43
    JNIEnv
    -0.41
    icestershire
    -0.41
    يكب
    -0.41
    govia
    -0.41
     Nijmegen
    -0.41
    хьтан
    -0.40
    POSITIVE LOGITS
     marine
    1.73
     coastal
    1.62
     seawater
    1.57
     ocean
    1.55
     maritime
    1.52
     Ocean
    1.52
     beach
    1.49
     Marine
    1.48
     seaside
    1.48
    Marine
    1.48
    Activations Density 1.703%

    No Known Activations