© 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. 18-GEMMASCOPE-RES-16K
    11. 1947
    Prev
    Next
    INDEX
    Explanations

    terms related to decision making and parameters in research or analytical contexts

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

    Comes before "is," "was," "will," or "may"

    np_acts-logits-general · gemini-2.0-flash

    reason for stemming

    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
    RegressionTest
    -0.70
    matchCondition
    -0.65
     Riproduzione
    -0.59
    LookAnd
    -0.59
     CreateTagHelper
    -0.57
     Houſe
    -0.57
     Anſ
    -0.56
    الإنجليزية
    -0.56
    XmlAccessorType
    -0.56
     Majefty
    -0.56
    POSITIVE LOGITS
    是因为
    1.12
    是因為
    1.12
     stems
    1.10
    是为了
    0.98
     stemmed
    0.96
     arose
    0.94
    理由は
    0.91
     disebabkan
    0.89
     wynika
    0.88
    之所以
    0.87
    Activations Density 0.736%

    No Known Activations