© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11206
    Prev
    Next
    INDEX
    Explanations

    terms related to coral species and marine biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     водя
    -0.37
     Schein
    -0.35
    สู
    -0.34
     Dost
    -0.33
     Bowles
    -0.32
    TestFixture
    -0.32
     eccl
    -0.32
    Odour
    -0.31
     Hudson
    -0.31
    chability
    -0.31
    POSITIVE LOGITS
     reef
    1.01
     coral
    0.95
     corals
    0.85
     Reef
    0.85
     reefs
    0.84
     Coral
    0.81
    reef
    0.78
    礁
    0.77
    coral
    0.76
    Coral
    0.76
    Activations Density 0.337%

    No Known Activations