© 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. 170
    Prev
    Next
    INDEX
    Explanations

    references to the term "Terra" and its variations in various contexts

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

    words starting with "Ter"

    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
     Schub
    -0.59
     Pouch
    -0.54
     Komunikasi
    -0.54
    Signup
    -0.53
     Apost
    -0.52
     Lait
    -0.51
     Penga
    -0.51
    ாள
    -0.51
    XmlAccessType
    -0.50
    OGND
    -0.50
    POSITIVE LOGITS
     Ter
    2.13
    Ter
    1.99
     ter
    1.68
     TER
    1.58
     Terrence
    1.20
     Terrell
    1.15
     Terence
    1.13
     Tera
    1.11
     Тер
    1.09
    ter
    1.05
    Activations Density 0.005%

    No Known Activations