© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15630
    Prev
    Next
    INDEX
    Explanations

    phrases related to political commentary or critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reit
    -0.43
     obti
    -0.42
     basic
    -0.42
    aus
    -0.41
     tends
    -0.41
     Basic
    -0.40
     layout
    -0.40
     tend
    -0.39
    基本
    -0.39
     довольно
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.59
     noDo
    0.52
    CloseOperation
    0.50
     IActionResult
    0.50
     presidencial
    0.50
     nargin
    0.49
     removeFrom
    0.48
    PostInfinity
    0.48
    хьтан
    0.45
     nationales
    0.45
    Activations Density 0.280%

    No Known Activations