Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5236
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function definitions and class declarations

    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
    +#+#
    -0.63
     GenerationType
    -0.57
    ValueStyle
    -0.55
    PageRoute
    -0.49
    onedDateTime
    -0.48
    InputBorder
    -0.48
    AddTagHelper
    -0.48
    MemoryWarning
    -0.48
     modelAndView
    -0.47
    Cyfarwyddwr
    -0.47
    POSITIVE LOGITS
     versatile
    0.40
     flexibilidad
    0.39
     flexibility
    0.39
    outils
    0.38
    apps
    0.37
     aguja
    0.37
     ciertamente
    0.37
    limo
    0.37
     øns
    0.36
     promesa
    0.36
    Activations Density 0.745%

    No Known Activations