© 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. 1481
    Prev
    Next
    INDEX
    Explanations

    punctuations and specific data structures or concepts in coding or technical contexts

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

    start of user code

    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
     escenarios
    -0.45
     oídos
    -0.43
     aleación
    -0.39
     historiador
    -0.38
    StringCopy
    -0.37
     finnas
    -0.36
     zví
    -0.36
     zvíř
    -0.35
     asesinado
    -0.35
     ancla
    -0.35
    POSITIVE LOGITS
     OnInit
    1.88
    OnInit
    0.85
    ExtendWith
    0.66
     NgModule
    0.63
    UnsafeEnabled
    0.59
    Vidite
    0.56
    httphttps
    0.56
     ModelAndView
    0.55
    NgModule
    0.55
     viewDidLoad
    0.54
    Activations Density 0.000%

    No Known Activations