© 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. 9105
    Prev
    Next
    INDEX
    Explanations

    significant numerical values and examples in a technical context

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

    Followed by "such"

    np_acts-logits-general · gemini-2.0-flash

    one such

    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
    hdashline
    -0.75
    Hauptartikel
    -0.68
    ')):
    -0.66
     kasarigan
    -0.65
    NameInMap
    -0.64
    🏽
    -0.63
     interchangeably
    -0.63
     Gaetano
    -0.62
    """.
    -0.62
    "):
    -0.61
    POSITIVE LOGITS
     such
    4.18
    such
    3.51
    Such
    3.42
     Such
    3.41
     SUCH
    2.92
     solche
    2.57
     solcher
    2.53
     solchen
    2.43
     таких
    2.33
     solches
    2.30
    Activations Density 1.560%

    No Known Activations