© 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. 14-GEMMASCOPE-RES-16K
    11. 8835
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of sentences or sections in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izieren
    -0.47
    ("/")
    -0.40
     dates
    -0.39
     lives
    -0.38
     steps
    -0.37
    рованные
    -0.36
    ex
    -0.35
    })));
    -0.35
    setDate
    -0.35
    com
    -0.35
    POSITIVE LOGITS
     Roskov
    1.14
    Personensuche
    0.86
    WriteTagHelper
    0.82
    IRUS
    0.81
    دانشنامهٔ
    0.76
    Geplaatst
    0.72
    TagMode
    0.71
     محفوظة
    0.71
     AssemblyTitle
    0.69
    írus
    0.69
    Activations Density 0.197%

    No Known Activations