© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12512
    Prev
    Next
    INDEX
    Explanations

    key actions and statistics related to sports plays and player performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.58
    zu
    -0.46
    دانشنامهٔ
    -0.46
    rungsseite
    -0.44
     регуляр
    -0.43
     potencial
    -0.43
    RAINT
    -0.43
     flor
    -0.43
    </i>
    -0.42
     estimés
    -0.42
    POSITIVE LOGITS
    VIAF
    0.77
     Paglinawan
    0.77
     Waray
    0.73
     CommonModule
    0.73
    ruptedException
    0.68
     ContentValues
    0.67
    InputTagHelper
    0.67
     JADX
    0.67
    ROIT
    0.67
    MockMvc
    0.65
    Activations Density 0.155%

    No Known Activations