© 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. 10-GEMMASCOPE-RES-16K
    11. 10962
    Prev
    Next
    INDEX
    Explanations

    phrases related to transformation or transitions into new forms or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    explique
    -0.45
    grunn
    -0.42
    RANGE
    -0.42
    Cevap
    -0.41
     introduced
    -0.40
     avut
    -0.40
     înce
    -0.39
    ofed
    -0.39
    introduced
    -0.39
     sə
    -0.38
    POSITIVE LOGITS
    WriteTagHelper
    0.89
     AssemblyCulture
    0.89
    ########.
    0.88
     autorytatywna
    0.87
    BeginContext
    0.86
     transférez
    0.85
     ujednoznacz
    0.80
     transfieras
    0.79
    ✨:
    0.75
    ImageContext
    0.74
    Activations Density 0.478%

    No Known Activations