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. 68590
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly Sinai and related areas

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

    Sinai, Suez, Seder

    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
    MessageTagHelper
    -0.52
    Obrázky
    -0.47
    ThroughAttribute
    -0.45
     Jør
    -0.40
    mphony
    -0.40
    Jolly
    -0.40
    SourceChecksum
    -0.39
    GtkWidget
    -0.39
     nakalista
    -0.38
    copg
    -0.37
    POSITIVE LOGITS
     Sinai
    2.94
    inai
    1.23
     Sina
    1.13
     Suez
    0.96
    sina
    0.77
     sina
    0.76
     Egypt
    0.69
     Sahara
    0.68
     Crete
    0.66
     Cairo
    0.65
    Activations Density 0.005%

    No Known Activations