© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 1681
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to characters and elements in a narrative or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.67
     الحره
    -0.48
     propOrder
    -0.46
     Roskov
    -0.45
    FontOfSize
    -0.43
     numberOfRows
    -0.43
    WaitGroup
    -0.43
     شعب
    -0.43
    Derbyniad
    -0.43
    FirstResponder
    -0.42
    POSITIVE LOGITS
     BoxDecoration
    0.53
    IConfiguration
    0.52
    LabelTagHelper
    0.47
     Мексичка
    0.43
     IConfiguration
    0.43
    labelControl
    0.42
    apunov
    0.42
    HttpPut
    0.41
    CloseOperation
    0.41
    logrus
    0.40
    Activations Density 3.640%

    No Known Activations