© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1623
    Prev
    Next
    INDEX
    Explanations

    terms related to encoding and compression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    viewpager
    -0.78
     Stoner
    -0.78
    ácara
    -0.78
     maxn
    -0.71
     year
    -0.68
     CGSize
    -0.68
    liesslich
    -0.68
    Obrázky
    -0.68
    tableFuture
    -0.67
    AsUp
    -0.65
    POSITIVE LOGITS
     encode
    1.52
     Encode
    1.49
    encode
    1.46
     encoded
    1.45
    Encode
    1.39
     encodes
    1.35
    encoded
    1.31
     Decode
    1.31
     encoding
    1.26
    Decode
    1.24
    Activations Density 0.129%

    No Known Activations