© 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. 68516
    Prev
    Next
    INDEX
    Explanations

    references to relocation and movement of entities or groups

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

    relocate

    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
    expandindo
    -0.70
     numberWith
    -0.60
    MenuInflater
    -0.57
     constexpr
    -0.56
    دانشنامهٔ
    -0.52
    GEBURTSDATUM
    -0.52
    aarrggbb
    -0.51
    Hamster
    -0.50
    printList
    -0.50
     AssemblyVersion
    -0.50
    POSITIVE LOGITS
     relocation
    1.86
     relocate
    1.81
     relocated
    1.73
     Relocation
    1.71
     relocating
    1.63
    location
    0.89
     translocation
    0.82
     Locate
    0.82
     LOCATION
    0.81
     locate
    0.81
    Activations Density 0.006%

    No Known Activations