© 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. 24-GEMMASCOPE-RES-16K
    11. 9166
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical measurement and optimization processes

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

    Minimizing a cost, loss, or error function

    np_acts-logits-general · gemini-2.0-flash

    minimizing cost function error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.62
    DebuggerNonUser
    -0.61
    WebServlet
    -0.58
    Seeder
    -0.55
     ProtoMessage
    -0.53
     TestBed
    -0.53
    ########.
    -0.50
    DidLoad
    -0.50
    BeginInit
    -0.49
    coln
    -0.48
    POSITIVE LOGITS
     loss
    1.01
     cost
    0.96
     objective
    0.93
     Loss
    0.87
    Loss
    0.85
    loss
    0.84
     minimized
    0.83
    Objective
    0.83
    cost
    0.82
    objective
    0.81
    Activations Density 1.066%

    No Known Activations