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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 1418
    Prev
    Next
    INDEX
    Explanations

    references to the word "Atlantis" and variations of the word "lat" as they relate to structure or themes associated with that concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Atlantic or Atlantis Rail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    LabelTagHelper
    -0.61
    tagHelperRunner
    -0.57
    uxxxx
    -0.52
    ViewFeatures
    -0.52
     endblock
    -0.52
    rungsseite
    -0.50
    __":
    
    -0.48
     bezeichneter
    -0.46
    shadowOffset
    -0.44
    .*")]
    -0.43
    POSITIVE LOGITS
    Atlan
    1.44
     Atlan
    1.35
    Atlantic
    1.27
     Atlantic
    1.27
     Atlantis
    1.24
     ATLANTIC
    1.17
     atlan
    1.14
     Atlántico
    1.11
     atlantic
    1.11
     Atl
    1.09
    Activations Density 0.011%

    No Known Activations