© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 51759
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the substring "eck"

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

    eck or Eck in names

    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
     Juanita
    -0.42
    Vivian
    -0.40
     Witten
    -0.40
     Vivian
    -0.40
     Lucien
    -0.39
     emin
    -0.39
     Hauptmann
    -0.39
     Opportun
    -0.38
     stimulants
    -0.37
    所
    -0.37
    POSITIVE LOGITS
    eck
    3.28
    ECK
    2.55
    ecks
    1.80
    Eck
    1.46
     Eck
    1.38
    ecke
    1.30
    ecka
    1.25
    ecki
    1.24
     Peck
    1.14
    ecker
    1.13
    Activations Density 0.004%

    No Known Activations