© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7193
    Prev
    Next
    INDEX
    Explanations

    terms related to programming errors and compatibility issues in code

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

    "old" or "previous"

    np_acts-logits-general · gemini-2.0-flash

    old or existing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bewerken
    -0.52
    альных
    -0.51
    VersionUID
    -0.49
    XmlType
    -0.47
     FetchType
    -0.45
    حيح
    -0.45
    ुष
    -0.43
    ValueGeneration
    -0.42
     ISNI
    -0.42
    Gemeinden
    -0.42
    POSITIVE LOGITS
     old
    2.94
    old
    2.47
     existing
    2.43
     older
    2.34
     oude
    2.25
     vecchia
    2.23
     vecchio
    2.22
     vecchi
    2.21
    existing
    2.16
     Existing
    2.16
    Activations Density 0.737%

    No Known Activations