© 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. 18-GEMMASCOPE-RES-16K
    11. 12365
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to meetings and group discussions

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

    "Such" followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    such phrases

    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
     kasarigan
    -0.61
    üksek
    -0.47
    wyl
    -0.45
    Foreword
    -0.45
     estri
    -0.44
     mxArray
    -0.43
    JoinTable
    -0.42
    foglal
    -0.42
    uttavia
    -0.41
    PLEMENT
    -0.40
    POSITIVE LOGITS
     such
    1.98
    such
    1.73
    Such
    1.71
     چنین
    1.65
    这样的
    1.63
     solche
    1.61
    這樣的
    1.58
     SUCH
    1.57
     Such
    1.56
     solchen
    1.53
    Activations Density 0.619%

    No Known Activations