© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1834
    Prev
    Next
    INDEX
    Explanations

    terms related to measuring instruments and their functions

    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
     mor
    -0.48
     AssemblyTitle
    -0.45
     churn
    -0.44
    行
    -0.40
    ordion
    -0.40
     Bott
    -0.40
    ècie
    -0.39
     Morin
    -0.39
     Chan
    -0.39
    香
    -0.39
    POSITIVE LOGITS
     nahilalakip
    0.46
    ſelves
    0.45
     ACCUR
    0.44
     ſta
    0.44
     ſtill
    0.43
    Accurate
    0.42
     Calibration
    0.42
    ſelf
    0.42
     vectorielle
    0.41
     viewDidLoad
    0.41
    Activations Density 0.811%

    No Known Activations