© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15659
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitioning phrases that indicate contrast or a change in thought

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

    followed by discourse markers

    np_acts-logits-general · gemini-2.0-flash

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReadAll
    -0.51
    总之
    -0.50
     et
    -0.48
    何より
    -0.47
    とにかく
    -0.44
    archiviato
    -0.44
     نکنید
    -0.44
    Anyways
    -0.43
     const
    -0.43
    ⁦
    -0.42
    POSITIVE LOGITS
    これは
    1.66
     this
    1.60
     isso
    1.59
    これが
    1.49
    这一点
    1.49
     это
    1.39
    これも
    1.37
    这点
    1.36
    Isso
    1.35
    这就
    1.34
    Activations Density 0.898%

    No Known Activations