© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8745
    Prev
    Next
    INDEX
    Explanations

    conjunctions and relational phrases that link ideas together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    causation or consequence

    np_acts-logits-general · gemini-2.0-flash

    and consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.55
     հղումներ
    -0.51
    ioutil
    -0.49
     AssemblyCulture
    -0.48
     PeEnEo
    -0.47
     EconPapers
    -0.44
    PerformLayout
    -0.43
     minOccurs
    -0.43
     iNdEx
    -0.42
    ★★★★☆
    -0.41
    POSITIVE LOGITS
     therefore
    2.56
     hence
    2.11
    therefore
    2.08
     thus
    1.98
     consequently
    1.82
     donc
    1.75
    Therefore
    1.67
     Therefore
    1.66
    hence
    1.65
     portanto
    1.64
    Activations Density 0.701%

    No Known Activations