© 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. 15408
    Prev
    Next
    INDEX
    Explanations

    expressions of quality or evaluation related to experiences

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

    Intensifiers like "very", "really", or punctuation

    np_acts-logits-general · gemini-2.0-flash

    degree and intensity

    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
    ="@+
    -0.58
    MENAFN
    -0.58
    queryInterface
    -0.56
     GenerationType
    -0.54
     onAnimation
    -0.52
    oneofs
    -0.51
     hini
    -0.49
    TagHelpers
    -0.49
     noqa
    -0.47
    Autoritní
    -0.47
    POSITIVE LOGITS
     very
    1.72
     VERY
    1.56
     Very
    1.53
    Very
    1.51
    VERY
    1.48
    very
    1.45
     extremely
    1.43
     REALLY
    1.28
     really
    1.27
    extremely
    1.25
    Activations Density 0.212%

    No Known Activations