© 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. 19-GEMMASCOPE-RES-16K
    11. 15229
    Prev
    Next
    INDEX
    Explanations

    concepts related to separation and connection within systems or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.78
     Normdatei
    -0.72
    MessageOf
    -0.71
    \{\\
    -0.69
    compared
    -0.69
     compared
    -0.65
    ijnen
    -0.64
    ]")]
    -0.63
     INTERESAR
    -0.62
     ""));
    -0.60
    POSITIVE LOGITS
     nhau
    0.64
    กัน
    0.49
     custodia
    0.44
     البعض
    0.43
     via
    0.42
     mutual
    0.42
    QtCore
    0.41
    BIDDEN
    0.41
    pyx
    0.40
     intime
    0.39
    Activations Density 0.514%

    No Known Activations