© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3915
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting comparisons or differences in quality or quantity

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

    French comparatives "plus", "moins", "très"

    np_acts-logits-general · gemini-2.0-flash

    comparative degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     very
    -0.90
     extremely
    -0.81
    Personendaten
    -0.77
     absolutely
    -0.77
    very
    -0.75
    Very
    -0.72
     Very
    -0.72
    VERY
    -0.72
     totally
    -0.71
     completely
    -0.69
    POSITIVE LOGITS
    ########.
    0.60
    writeFieldEnd
    0.52
     rappresent
    0.49
    اعمال
    0.47
    astéroïdes
    0.46
    cropping
    0.45
     demanded
    0.43
    itieren
    0.43
    awaiter
    0.43
     verlangt
    0.42
    Activations Density 0.095%

    No Known Activations