© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 522
    Prev
    Next
    INDEX
    Explanations

    references to oral administration or intake

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.85
    awtextra
    -0.73
     Greer
    -0.73
    ค์
    -0.72
    ed
    -0.72
    MockBean
    -0.71
     Meksiku
    -0.70
     Versace
    -0.70
     IBOutlet
    -0.69
     javax
    -0.68
    POSITIVE LOGITS
     Ownership
    1.01
    Ownership
    0.85
     ownership
    0.82
    ownership
    0.81
    UMBIA
    0.79
    olidation
    0.76
     Supervisors
    0.76
    脚注の使い方
    0.76
    hiculo
    0.72
    addPreferredGap
    0.71
    Activations Density 0.092%

    No Known Activations