© 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. 5843
    Prev
    Next
    INDEX
    Explanations

    HTML elements associated with a container layout structure

    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
    ientí
    -0.45
    Aix
    -0.41
    irability
    -0.41
     Análisis
    -0.40
    Politique
    -0.40
    GRAFÍA
    -0.40
     Mejora
    -0.40
    hance
    -0.40
    LError
    -0.39
    aspectj
    -0.39
    POSITIVE LOGITS
     container
    2.28
     Container
    2.27
    container
    2.14
    Container
    2.09
     containers
    1.87
     Containers
    1.85
    CONTAINER
    1.80
    Containers
    1.58
    容器
    1.53
     контей
    1.51
    Activations Density 0.071%

    No Known Activations