© 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. 11-GEMMASCOPE-RES-16K
    6. 5422
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferons
    -0.35
     persoonlijke
    -0.33
    บัติ
    -0.33
    别
    -0.33
     kantoor
    -0.31
     dovrebbe
    -0.31
     prijzen
    -0.30
     elkaar
    -0.30
    要不要
    -0.29
    cientos
    -0.29
    POSITIVE LOGITS
    providedIn
    0.75
    RegressionTest
    0.71
     EconPapers
    0.71
     HasFactory
    0.70
     WebDriverWait
    0.63
     InputDecoration
    0.62
    хьтан
    0.62
    usercontent
    0.61
    OGND
    0.61
    BASEPATH
    0.61
    Activations Density 0.270%

    No Known Activations